Nuova ricerca

MARTIN KLAPEZ

Ricercatore t.d. art. 24 c. 3 lett. A
Dipartimento di Ingegneria "Enzo Ferrari"

Home |


Pubblicazioni

2023 - Awareness Messages by Vulnerable Road Users and Vehicles: Field Tests via LTE-V2X [Articolo su rivista]
Lusvarghi, Luca; Grazia, CARLO AUGUSTO; Klapez, Martin; Casoni, Maurizio; Merani, Maria Luisa
abstract

2022 - Aggregating Without Bloating: Hard Times for TCP on Wi-Fi [Articolo su rivista]
Grazia, CARLO AUGUSTO; Patriciello, Natale; Høiland-Jørgensen, Toke; Klapez, Martin; Casoni, Maurizio
abstract

2021 - Experimental Evaluation of IEEE 802.11p in High-Speed Trials for Safety-Related Applications [Articolo su rivista]
Klapez, Martin; Grazia, CARLO AUGUSTO; Casoni, Maurizio
abstract

2021 - The Energy Footprint of 5G Multi-RAT Cellular Architectures [Articolo su rivista]
Klapez, M.; Grazia, C. A.; Casoni, M.
abstract

While environmental and financial reasons point to the minimization of the number of radio sites to contain energy use, emissions, and operating expenses of cellular networks, the industry has, in retrospect, partly headed in the opposite direction. The reasons are the deployment of new technologies alongside the existing ones, the use of higher frequencies, and the expansion of radio coverage. In some cases, the issue has been addressed by replacing legacy access sites with Multi-RAT infrastructures, composed of individual radio elements that run multiple technologies concurrently. Now, the transition to 5G poses additional challenges. This paper reviews Multi-RAT architectures, outlines their benefits, discusses how 5G can be integrated, and provides guidance in terms of architectural recommendations, all from an energy consumption standpoint. Specifically, we firstly summarize the transition of monolithic base stations into modern radio elements, exposing the energy rationale and discussing the impact of each main network component. From this basis, we survey different deployment strategies and evaluate their energy implications in light of the constraints and opportunities given by the 5G New Radio standard, its flagship applications, and its transport requirements. Then, we lay down energy-saving estimates quantifying the contribution of each main network segment, revealing the most promising architectures, and identifying the main challenges and the research directions ahead.

2021 - The Impact of Transmission Power on the Safety-Related Performance of IEEE 802.11p [Relazione in Atti di Convegno]
Klapez, M.; Grazia, C. A.; Casoni, M.
abstract

In this paper, we report and analyze results from a field test campaign aimed at assessing the real-world performance of IEEE 802.11p for safety-related applications. Regulator bodies in the EU and the US recommend the use of domestic-level transmission powers for general usage while granting the opportunity of employing higher powers for safety purposes. While the latter are generally expected to result in higher network performance, we want to quantitatively assess what they translate to in terms of metrics relevant from an application point of view, such as, goodput, round-trip times, jitter, and losses. These are studied and associated with conditions out of the network control at urban and suburban speeds, that is, in absence or in presence of different degrees of congestion, and in complete or partial line-of-sight. In general, we find evidence of an inverse correlation between the degree of congestion and the benefits granted by higher transmission powers. Up to the tested speed, IEEE 802.11p appears able to provide safety guarantees even at relatively long distances, as long as an appropriate transmission power is employed. At the same time, it must be acknowledged that higher power alone cannot overcome the significant dips in performance resulting from highly congested environments and non-line-of-sight scenarios.

2021 - The new TCP modules on the block: A performance evaluation of TCP Pacing and TCP Small Queues [Articolo su rivista]
Grazia, CARLO AUGUSTO; Klapez, Martin; Casoni, Maurizio
abstract

2020 - Application-Level Performance of IEEE 802.11p in Safety-Related V2X Field Trials [Articolo su rivista]
Klapez, Martin; Grazia, CARLO AUGUSTO; Casoni, Maurizio
abstract

2020 - BBR+: Improving TCP BBR Performance over WLAN [Relazione in Atti di Convegno]
Grazia, C. A.; Patriciello, N.; Klapez, M.; Casoni, M.
abstract

This paper shows the inefficiency of TCP BBR in exploiting the Wi-Fi bandwidth. This limitation of BBR has been observed with both IEEE 802.1ln and IEEE 802.11ac, where the mechanism of frame aggregation is used to boost the throughput of data transmission. In the last years, many TCP variants have been introduced to limit the bufferbloat phenomena and bound the latency, through a reduction of the queue backlog injection rate. However, this mechanism impacts on the Wi-Fi frame aggregation logic, impeding TCP congestion controls to reach the full throughput potential of a Wi-Fi interface. While this problem can be solved with TCP CUBIC allowing the sender node to enqueue more packets, for TCP BBR the fix is not the same, as it has a customized pacing algorithm. With this contribution, we propose BBR+, a new BBR version that allows to fine tune the congestion control pace, achieving 6 times more throughput over IEEE 802.1ln channels and 16 times more throughout over IEEE 802.11ac channels, at the cost of an increased latency that is however always less than the latency obtainable with TCP CUBIC.

2020 - BBRp: Improving TCP BBR Performance over WLAN [Articolo su rivista]
Grazia, C. A.; Klapez, M.; Casoni, M.
abstract

This paper shows the inefficiency of TCP BBR in exploiting the Wi-Fi bandwidth. This limitation of BBR has been observed with both IEEE 802.11n and IEEE 802.11ac, where the mechanism of frame aggregation is used to boost the throughput of data transmission. In the last years, many TCP variants have been introduced to limit the bufferbloat phenomena and bound the latency through a reduction of the queue backlog injection rate. However, this mechanism impacts on the Wi-Fi frame aggregation logic, impeding TCP congestion controls to reach the full throughput potential of a Wi-Fi interface. While this problem can be solved with TCP Cubic by allowing the sender node to enqueue more packets, for TCP BBR the fix is not the same, as it has a customized pacing algorithm. With this contribution we propose BBRp, a new BBR version that allows for fine-tuning the congestion control pace, achieving between four and six times more throughput over IEEE 802.11n and IEEE 802.11ac channels, at the cost of an increased latency that is however always less than the latency obtainable with loss-based TCP congestion controls.

2020 - IRONMAN: Infrastructured RSSI-based opportunistic routing in mobile adhoc networks [Relazione in Atti di Convegno]
Grazia, C. A.; Klapez, M.; Casoni, M.
abstract

V2X technologies are based on heterogeneous and safety-related applications that rely on broadcast messages, which are typical in V2V communications, and to unicast messages, which are, instead, typical in V2I/I2V communications. To ease unicast communications from the infrastructure to the vehicle, like rescue operations, addressing the challenging routing aspect for VANETs, we designed an Infrastructured RSSI-based Opportunistic routiNg algorithm for Mobile Adhoc Networks (IRONMAN), also focusing on the energy consumption of the solution developed. IRONMAN takes opportunistic routing decisions based on the RSSI calculated by the Road-Side Units (RSUs), instead of the classical GPS-based solutions. Through a real testbed, we demonstrate that IRONMAN outperforms standard Linux-based routing solutions for ad-hoc networks, like BATMAN and HWMP, providing almost optimal goodput without adding any overhead related to the routing decisions.

2020 - Minimization of IEEE 802.11p Packet Collision Interference through Transmission Time Shifting [Articolo su rivista]
Klapez, Martin; Grazia, CARLO AUGUSTO; Casoni, Maurizio
abstract

2019 - IEEE 802.11p field trials on interference minimization for safety-related V2X applications [Relazione in Atti di Convegno]
Klapez, M; Grazia, C. A.; Casoni, M
abstract

In this work, we focus on the well-known hiddenterminal problem applied to the IEEE 802.11p context, from aninfrastructure-centric point of view (I2V). The problem occursin scenarios where two nodes are out of each other’s rangewhile being independently able to communicate with a thirdthat, intuitively speaking, is positioned in the middle of theformer two. If the two nodes transmit to the third at the samefrequency and at the same time, though not exactly the samesignal, the third would be unable to identify the two sourcesignals and, therefore, would suffer from interference. Althoughthe occurrence of this problem may be unlikely in I2V practice,certain applications, such as road safety, require the problemto be addressed anyhow. This article shows the outcomes offield trials conceived to experience first-hand the occurrence ofthe issue in IEEE 802.11p networks, experiment with differentinterference management techniques, and design or select theoptimal approach to minimize interference. Results unequivocallyattest that, in this context, an ad-hoc Time-Division MultipleAccess (TDMA) approach provides the best guarantees in anycondition. It is also shown how, on the other hand, the commonmethod of using the Request To Send/Clear To Send (RTS/CTS)protocol to prevent the issue in unicast scenarios may result ina disappointing performance, due to the nature of safety-relatedI2V communications that employ short packets to be deliveredwith minimum latency.

2019 - IEEE 802.11p under congestion in an Infrastructure-to-Vehicle communication approach [Relazione in Atti di Convegno]
Klapez, M; Grazia, C. A.; Rold, L.; Casoni, M
abstract

Possible applications of the so-called Intelligent Transportation Systems, or connected vehicles, range from critical to trivial and comprise road safety, traffic and transportation efficiency, and infotainment. The networks underlying these applications are under development and test, but few works are available in the literature that present results from real testbeds. This article is about the performance of IEEE 802.11p networks under congestion in vehicular environments, analysed from an infrastructure-centric point of view. In particular, as no assumptions are made about the communication behavior of vehicles, the paper is a starting point in answering the question of how much guarantees the standardized technologies are able to provide in worst-case scenarios of network congestion. An IEEE 802.11p first physical testbed has been developed, and it has been used to perform tests on latency, bandwidth, and packet losses with real network traffic. Although to answer the question completely tests with farther distances and different devices have to be made, these first results appear promising. The RoadSide Units ability to deliver critical messages does take a hit during signaling storms generated by vehicles, but due to the small size and connection-less nature of the packets expected to be employed, some bandwidth remains available, although some redundancy mechanism, carefully designed, might be needed to overcome relatively high packet loss ratios.

2019 - Processing and Communication Delays in EWS: On the Performance of the Earthcloud Prototype [Articolo su rivista]
Klapez, M.; Grazia, C. A.; Casoni, M.; Zennaro, S.; Cozzani, M.
abstract

A Seismic Alert System (SAS), also called Earthquake Warning System (EWS) or Earthquake Early Warning System (EEW or EEWS), represents one of the most important measures that can be taken to prevent and minimize earthquake damage. These systems are mainly used to detect P-waves and the faster seismic waves and to subsequently trigger an alarm about the incoming S-waves, the slower and most dangerous seismic waves. In some cases, distributed systems are also able to alert some locations before the impending P-waves strike them. This paper presents Earthcloud, a cloud-based SAS that aims to provide all the former capabilities while retaining financial accessibility. Earthcloud first results, generated from four months of data acquisition, are compared with those coming from other systems. In particular, the paper focuses on processing and communication delays, showing how the Earthcloud new detection strategy may minimize delays. Although a thorough test campaign with more sensor nodes is needed to assess performance reliably, especially for highly dense urban scenarios, initial results are promising, with total latencies for Earthcloud always kept under the 1-second mark, despite being at the expense of solid magnitude estimation.

2019 - Transmission Control Protocol and Active Queue Management together against congestion: cross-comparison through simulations [Articolo su rivista]
Grazia, Carlo Augusto; Patriciello, Natale; Klapez, Martin; Casoni, Maurizio
abstract

Most Internet traffic is carried by the Transmission Control Protocol (TCP) nowadays, even in the case of real-time services. Detecting and mitigating the congestion is one of the primary tasks of this protocol, in fact, different TCP versions are defined by their congestion control algorithms. Furthermore, Active Queue Management (AQM) algorithms share the same goal of congestion mitigation with TCP; in particular, the most efficient congestion control occurs when AQM and TCP work together. This paper presents a brief survey and a cross-comparison of the latest and most important TCP and AQM variants, then provides an evaluation of a different kind of performance on the ns-3 network simulator over various types of environments (multiple Round Trip Time, long delay, different congestion levels, etc.). In any shared bottleneck, the choice of the TCP-AQM couple to adopt is crucial. We will show that the results are not univocal and the “one size fits all” solution does not exist. Moreover, the proper couple depends on the performance that we want to boost and on the environment that we have to deal with.

2018 - A hybrid algorithm to combine redundancy and concurrency in virtual network resource pooling [Articolo su rivista]
Klapez, M.; Grazia, C. A.; Casoni, M.
abstract

Emergency scenarios pose significant hurdles to wireless communications, especially when these are performed through terrestrial cellular networks. This is because network infrastructures can be damaged, or the sudden surge of network demand can cause unbearable network congestion. Unfortunately, public safety operators employ terrestrial cellular networks to perform data communications and are therefore at risk of being unable to effectively operate in critical situations. Virtual network resource pooling is a software-defined networking (SDN)-based network framework that allows collaborative hosts to pool together their network channels to provide connectivity despite the sudden unavailability of network paths or to compensate for high degrees of packet losses. Once hosts’ resources are pooled, a dispatching algorithm on the SDN controller is required to enforce a proper policy of packets distribution. This paper presents a dispatching algorithm that is designed to provide fast and reliable transmissions despite lossy and unreliable channels. It works by introducing the minimum amount of packet redundancy that is needed to obtain a packet delivery probability given as a parameter and by using the remaining network resources to augment transfer goodput. Emulation results confirm that with respect to policies that selectively aim to improve goodput or to introduce packet redundancy, this hybrid algorithm can compensate for high packet loss ratios and improve goodput at the same time.

2018 - Adapting TCP Small Queues for IEEE 802.11 Networks [Relazione in Atti di Convegno]
Grazia, C. A.; Patriciello, N.; Høiland-Jørgensenz, T.; Klapez, M.; Casoni, M.; Mangues-Bafalluy, J.
abstract

In recent years, the Linux kernel has adopted an algorithm called TCP Small Queues (TSQ) for reducing queueing latency by controlling buffering in the networking stack. This solution consists of a back-pressure mechanism that limits the number of TCP segments within the sender TCP/IP stack, waiting for packets to actually be transmitted onto the wire before enqueueing further segments. Unfortunately, TSQ prevents the frame aggregation mechanism in the IEEE 802.11n/ac standards from achieving its maximum aggregation, because not enough packets are available in the queue to build aggregates from, which severely limits achievable throughput over wireless links. This paper demonstrates this limitation of TSQ in wireless networks and proposes Controlled TSQ (CoTSQ), a solution that improves TSQ so that it controls the amount of data buffered while allowing the IEEE 802.11n/ac aggregation logic to fully exploit the available channel and achieve high throughput. Results on a real testbed show that CoTSQ leads to a doubling of throughput on 802.11n and up to an order of magnitude improvement in 802.11ac networks, with a negligible latency increase.

2018 - Energy Savings of Sleep Modes enabled by 5G Software-Defined Heterogeneous Networks [Relazione in Atti di Convegno]
Klapez, M.; Grazia, C. A.; Casoni, M.
abstract

The current base station centric cellular network architecture hinders the implementation of effective sleep techniques, often resulting in energy-inefficient mobile networks. The efforts towards 5G and network densification, however, open new possibilities and may, at last, allow the integration of sleep modes without any QoS degradation. In this paper, we consider heterogeneous networks in which data and control planes are split and independent, referred to as SDHN. We present an energy consumption metric that can be used to evaluate the radio access power consumption and the associated energy efficiency of these networks. Concerning other metrics in literature, the proposal accounts for both the coverage area as well as the traffic load, and it is relatively simple to use. The proposed metric is applied to evaluate the power consumption performance of an LTE SDHN in an urban indoor scenario. Results confirm that sleep modes in such architectures can effectively cut power consumption and improve energy efficiency while preserving QoS.

2018 - First Experiences with Earthcloud, a Low-Cost, Cloud-Based IoT Seismic Alert System [Relazione in Atti di Convegno]
Klapez, M.; Grazia, C. A.; Zennaro, S.; Cozzani, M.; Casoni, M.
abstract

A Seismic Alert System (SAS) is one of the most important measures that can be taken to prevent and minimize earthquake damage. The role of a SAS is to detect as soon as possible an earthquake in progress and to then immediately alert about the impending earthquake waves all locations in danger. Clearly, to be of any utility, the communication of the alarm has to be transmitted way faster than the propagation speed of the earthquake waves. This paper presents the rationale, setup and first results of a deployed Earthcloud prototype, an experimental SAS designed to be low-cost, low-power, and cloudbased. Earthcloud is devised to alert locations that are not too close yet not too far from the earthquake epicenter, i.e., those that can benefit from an alarm received from a few seconds to tens of seconds earlier. The system has been designed to leverage existing Internet infrastructures in order to perform both computation and communication in the cloud, minimizing costs and maximizing communication speed and deployment ease. Data harvested by Earthcloud has been cross-referenced with data from the Italian National Institute of Geophysics and Volcanology and, although still in a prototype stage, the first results indicate that the system can correctly detect earthquakes.

2018 - Quantifying Sleep-Related Energy Savings in Indoor LTE HetNets Radio Access [Relazione in Atti di Convegno]
Klapez, M.; Grazia, C. A.; Casoni, M.
abstract

While Sleep techniques show great promises in reducing the energy consumption of mobile networks, the necessity of providing “always-on” services with current cellular architectures significantly hinders the introduction of effective Sleep modes. As the process of network densification goes forward, it is paramount to lower to a minimum the additional energy consumption required by the deployment of more and more network sites. Fortunately, the deployment of Heterogeneous Networks opens new possibilities for the integration of simpler and highly effective Sleep technologies. In this paper, we evaluate and quantify the energy savings attainable by the latest Power Modulation and Sleep modes in a Heterogeneous LTE Network deployed to serve a traffic-intensive urban office area. Power consumption figures are based on those of real cells currently available on the market. Results indicate that the combination of Power Modulation and Sleep techniques is able to cut in half the energy required by the modeled Heterogeneous Network and that Sleep modes, in particular, can be the most beneficial.

2018 - The Bufferboost Effect: when Drops and Redundancy boost the Throughput [Relazione in Atti di Convegno]
Grazia, C. A.; Klapez, M.; Casoni, M.
abstract

In this paper, we present and characterize a phenomenon that arises when network congestion is met with packet redundancy at a distributed bottleneck. Congestion typically causes packet drops at the queueing level, especially when Active Queue Management techniques are employed to mitigate the bufferbloat effect. Redundancy may be present in the form of packet replication over different paths, as a solution to increase network resilience and network availability guarantees. When both network congestion and packet redundancy are in place, a counterintuitive throughput-boosting effect may originate from them. We named this phenomenon bufferboost, for the key role played by packet drops introduced to avoid bufferbloat effects. The contributions of this paper are the definition of the bufferboost phenomenon, its modelling through a mathematical upper bound formulation, its isolation in an emulated environment for reproducibility and its validation through an extensive numerical evaluation that also verifies the introduced model. Results show that bufferboost is a favorable side effect able to boost network throughput.

2017 - A Cross-Comparison between TCP and AQM Algorithms: which is the Best Couple for Congestion Control? [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; Patriciello, Natale; Klapez, Martin; Casoni, Maurizio
abstract

Current Internet traffic is carried mainly by the Transmission Control Protocol (TCP), and the performance of the Internet depends strongly on how well TCP works. Detecting and mitigating the congestion is one of the main tasks of this protocol, in fact, different TCP versions are defined by their congestion control algorithm. Also, Active Queue Management (AQM) algorithms share the same goal of congestion mitigation with TCP, in particular, the most effective congestion control occurs when AQM and TCP work together. This paper presents a brief survey and a cross-comparison of the latest and most important TCP and AQM variants, then provides an evaluation of a different kind of performance (multiple Round-Trip Time, long delay, different congestion level, etc.) on the ns-3 network simulator over various types of environments. In a shared bottleneck, the choice of the TCP-AQM couple to adopt is crucial; we show that the results are not univocal, the “golden couple” depends on the performance that we want to boost and on the environment that we have to deal with.

2017 - A software-defined 5G cellular network with links virtually pooled for public safety operators [Articolo su rivista]
Casoni, Maurizio; Grazia, Carlo Augusto; Klapez, Martin
abstract

During disaster relief operations, public safety personnel performs data communication almost exclusively through terrestrial commercial networks. However, common cellular infrastructures are often unable to provide acceptable throughput and even basic availability owing to congestion or infrastructural disruption. In order to overcome these issues, this paper proposes the implementation of a network abstraction that we define as virtual resource pooling. This allows to virtually pool the resources provided by the cellular channels on which field operators are connected. The proposal aims to harmoniously blend together the multihoming capabilities of modern devices and their collaborative potential by leveraging the software-defined networking facilities that are expected to be present in the core infrastructures of fifth-generation networks. Coupled with the envisioned performance and packet core plasticity of the latter, such a system may have the potential to provide future public safety operators with broadband capabilities and high quality of experience in day-to-day tasks and major planned events while providing improved communication guarantees in unplanned disasters. To experimentally assess our proposal, we present a test bed that has been built and used to perform network emulation runs and to extract their results. These indicate that a system with virtual resource pooling may greatly enhance not only throughput and quality of service properties but also the resilience guarantees that network tenants may offer to field operators.

2017 - How to avoid TCP Congestion without dropping Packets: an Effective AQM called PINK [Articolo su rivista]
Casoni, Maurizio; Grazia, Carlo Augusto; Klapez, Martin; Patriciello, Natale
abstract

This paper proposes PINK (Passive INverse feedbacK), a queue management algorithm designed to indi- rectly impose a certain resource allocation policy on defined sets of client hosts. PINK adds intelligence at intermediate nodes that connect client hosts to bottleneck links or to external networks in general, al- lowing these nodes to dynamically modify the TCP Acknowledgements (ACKs) segments passing through. The modification consists in replacing advertised Receive Window fields (RCV.WNDs) with custom values, in order to enforce a specific bandwidth utilization upper bound. To compute new RCV.WND values, PINK needs only the number of active connections, the flows RTTs and the transmission channel bandwidth. It follows that PINK permits to impose a centralized bandwidth management without the cooperation of clients, which means that no modification or addition to end hosts is needed. Furthermore, as demon- strated in this paper, our proposal does not constrain client hosts performance without purpose; on the contrary, PINK improves efficiency on multiplexed channels by exploiting their capacity and by main- taining a low queuing delay and guarantees optimal flow fairness without forcing any packet drop. We validate PINK performance in multiple scenarios by using the ns-3 network simulator.

2017 - Mitigating Congestion and Bufferbloat on Satellite Networks through a Rate-Based AQM [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; Patriciello, Natale; Klapez, Martin; Casoni, Maurizio
abstract

Satellite networking is known to suffer from specific network performance issues, such as high latency and low throughput stability; this derives mainly from the high propagation delay, in particular with GEO satellites. This characteristic poses limitations on the benefits that general AQM solutions could introduce; in fact, reducing congestion and mitigating queueing delay is a vital feature that could boost the performance of satellite networks. This paper investigates PINK (Passive INverse feedbacK), a queue management algorithm designed to indirectly impose an individual resource allocation policy in order to mitigate the bufferbloat effect and the network congestion while exploiting the channel throughput and guaranteeing optimal flow fairness without forcing any packet drop. PINK modifies the TCP Acknowledgements (ACKs) segments passing through the Satellite access gateway. The modification consists in replacing the advertised Receive Windows field (RCV.WNDs) with custom values, in order to enforce a particular bandwidth utilization upper bound. To compute new RCV.WND values, PINK needs only the number of active connections, the flows RTT and the transmission channel bandwidth. The design characteristics of this new AQM let it works efficiently in satellite networks, and we validate this statement through several simulations performed with the ns-3 network simulator.

2017 - Reducing Cellular Networks Power Consumption: the Role of Resource Pooling and Cooperation [Relazione in Atti di Convegno]
Klapez, Martin; Grazia, CARLO AUGUSTO; Casoni, Maurizio
abstract

This paper discusses the role that resource pooling and cooperation may play in reducing the ever-growing power consumption of cellular networks. These two abstractions are often referred to as methods to enhance communication throughput and increase data transmission resilience. The goal of this work is to advocate and highlight that they can also represent effective directions to go through in order to save significant amounts of energy and consequently reduce the greenhouse gas emissions generated by cellular communications. To demonstrate their potential, this paper presents a network abstraction called Virtual Resource Pooling, that has been designed to enable transparent, network-aware, and massively multipath transmissions through a harmonious integration between the multi-homing capabilities of modern devices and their collaborative potential. In addition to a notional presentation, the paper includes network emulation results that lay out the potential improvements of the proposal to network efficiency. These indicate that the system can scale transmission performance linearly with the number of concurrently forwarding nodes, effectively allowing to harness the unused network resources, and enabling to decouple the network’s energy consumption from the average QoE perceived by users.

2017 - SDN-Based Resource Pooling to Provide Transparent Multi-Path Communications [Articolo su rivista]
Casoni, M.; Grazia, C. A.; Klapez, M.
abstract

Fueled by the ever growing consumption of digital content and services, providers of packet- switched networks suffer more and more a conflict between network engineering constraints and end-user usage patterns. This conflict is due to the fact that deployed networks exhibit low efficiency in their average resource utilization rate, which stands opposed to, at times, unsatisfiable resource request peaks generated by users. Multipath transmissions are theoretically able to temper this offset, but have been an uphill road due to the complexity they require to dominate. This article proposes a network paradigm able to transparently provide end users with such capabilities, by virtually pooling network resources through Software-Defined Networking. It is shown how this discipline may be deployed in current network infrastructures, while complying with the main 5G architectures envisaged so far. It is advocated how such an effort may allow service providers to meet users’ expectations and strengthen profits without the need for unbearable financial investments, at the same time seamlessly improving their networks’ performance, reliability, resource utilization efficiency and energy consumption. To demonstrate the technical feasibility and the potential benefits of the proposed approach, we present a set of emulation results showing that the sweet spot between n-fold performance increases and robust resilience properties can be practically met.

2017 - Which AQM fits IoT better? [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; Patriciello, Natale; Klapez, Martin; Casoni, Maurizio
abstract

Most of the Internet traffic is carried by Transmission Control Protocol (TCP) nowadays, even in the case of real-time services and IoT environments. A key point of each TCP variant that defines the specific variant trademark is the congestion control algorithm. This congestion control, alone, is not able to mitigate the congestion problem completely; the most efficient solution, to be coupled with it, is the Active Queue Manager (AQM). In this paper, we analyze the response to congestion provided by the novel AQMs when coupled with popular TCP variants and, has happened in IoT networks, with a mix of TCP variants simultaneously active on the network. We provide extensive simulations within ns-3 to highlight what is the better AQM solution for IoT networks by considering the TCP algorithm and other environmental conditions like the number of active nodes, the network RTT and the presence of multiple RTT flows. We collected network metrics like throughput, goodput, latency, RTT variation, flows’ fairness and a simple drop analysis.

2016 - A Congestion Control Middleware Layer with Dynamic Bandwidth Management for Satellite Communications [Articolo su rivista]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

Historically, satellites have been set aside for what regards Internet connectivity; however, the interest in their usage to provide Internet connectivity is now rising again. Because of the growing demand for Internet services around the world, satellites can be an effective medium to serve scarcely populated areas as well as missioncritical communications. While the standard transmission control protocol (TCP) performs badly when employed on satellite links for the high propagation delay, when a number of client hosts are wirelessly connected to a gateway that forwards and receives traffic across such links, the major limit is represented by the channel condition estimation performed by the TCP through loss detection and/or acknowledgement-based timing information. This paper proposes congestion control middleware layer (C2MLC), a centralized and collaborative middleware with dynamic bandwidth management, that aims to improve performance and QoS for TCP flows in the aforementioned scenarios. Results of ns-3 simulations show an improvement in aggregate throughput, a significant reduction of latencies because of low queues occupancy levels, and higher fairness and friendliness guarantees among flows. They also confirm that C2MLC allows a dynamic and efficient usage of the bottleneck link, avoiding a waste of resources when some client nodes are unable to fully exploit their transmission potential.

2016 - An SDN and CPS based opportunistic Upload Splitting for mobile users [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin
abstract

This paper proposes an hybrid approach composed by Software Defined Networking (SDN) and Cyber-Physical Systems (CPS) to boost the upload speed of mobile users in low-bandwidth environments through a next generation Mobile Collaborative Community (MCC). The core idea is to use a high-bandwidth local communication system, like IEEE 802.11 (WiFi), in order to distribute data efficiently through mobile hosts; then, the distributed data may be sent from each mobile node to the original destination through their low-bandwidth mobile interface for wide area network communication. With our solution some drawbacks of MCC are faced. With the use of SDN we defined a flexible and easy-to-configure MCC system which operates in a transparent way for the end hosts. At the same time, the use of CPS creates a feedback for the system regarding the hosts channel status; this way the system is able to fully exploit the MCC potential by increasing the upload speed for both congested and non-congested scenarios.We demonstrate the efficiency of our solution through experimental results obtained using the Mininet network emulator where POX and a Pyretic controller serve as a dynamic data repartition engine.

2016 - Enabling Resource Pooling in Wireless Networks through Software-Defined Orchestration [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin
abstract

This paper proposes a network paradigm where network resources are virtually pooled through an OpenFlow controller that serves as the network orchestrator. The benefits that our proposal may guarantee with respect to the solutions currently published in literature are the installation, configuration and implementation simplicity, strong expandability properties, fallback behavior if needed, resilience to link failures, improvement of uplink data rates in addition to the downlink and, last but not least, the compatibility with common equipment, as no ad-hoc network protocols are needed. To assess the performance of our proposal, we present the test bed that has been built and used to extract the emulation results. Depending on the network characteristics, it is shown how an efficient orchestrator may succeed in allowing users to efficiently exploit the available network resources. We also show how, even in the worst-cases, the proposal exhibits significant performance improvements with respect to transfers where resources are not pooled among hosts.

2016 - Enabling Smart Environments by avoiding TCP Congestion through PINK: a no-drop AQM [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; Patriciello, Natale; Klapez, Martin; Casoni, Maurizio
abstract

This paper proposes PINK (Passive INverse feed-bacK), a queue management algorithm designed to indirectly impose a certain resource allocation policy on defined sets of client hosts. PINK adds intelligence at intermediate nodes that connect client hosts to bottleneck links or to external networks in general, allowing these nodes to dynamically modify the TCP Acknowledgments (ACKs) segments passing through. This is made by setting TCP ACK advertised Receive Windows field (RCV.WNDs) to custom values, in order to enforce a specific bandwidth utilization upper bound. To compute new RCV.WND values, PINK needs only the number of active connections, the flows RTTs and the transmission channel bandwidth. It follows that PINK permits to impose a centralized bandwidth management without the cooperation of clients, which means that no modification or addition whatsoever to end hosts is needed with the goal of enabling a smart environment by simply configuring the access node. Furthermore, as demonstrated in this paper, our proposal does not constraints client hosts performance without purpose; on the contrary, PINK improves efficiency on multiplexed channels by exploiting channel throughput, main- taining a low queuing delay, and guaranteeing optimal flow fairness without forcing any packet drop.

2016 - Towards Massively Multipath Transmissions for Public Safety Communications [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; Klapez, Martin; Casoni, Maurizio
abstract

During their day-to-day tasks, public safety operators rely on commercial mobile networks in order to perform data communications and make use of data-based services. In major disasters, however, it is the norm to witness high degrees of network congestion and, often, to experience service outages caused by infrastructural damage. This may strongly hinder the operativity of emergency operators, that expect to rely on resilient communication infrastructures and that demand network availability no matter what. In order for today mobile networks to provide such capabilities, some degree of redundancy should be introduced, either in hardware as infrastructural deployments or in software as data replication mechanisms. This paper focuses on the latter approach. It proposes a network framework to enable collaborative hosts to concurrently forward replicated data over an arbitrary number of channels, in order to compensate for high packet losses or sudden unavailability of routing paths. The data replication and the forwarding behavior are concerted by an SDN controller, that transparently implements a network abstraction to virtually pool hosts network resources. The paper also presents the test bed that has been built and used to extract the emulation results. These demonstrate that the proposal have the potential to strongly improve data communication capabilities in constrained scenarios, in the form of higher data rates and stronger resilience guarantees. Last but not least, it is shown that services availability may be provided in much more cases, even when regular operativity fails.

2015 - A Cooperative Middleware for Enhancing TCP Performance over High Delay Networks [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

When multiple nodes share the same gateway or access the same link, the throughput of wireless communications has the unfortunate problem of being limited by traffic congestion; the situation may also further degrade if they establish multiple TCP connections mapped over the same access channel. In end-to-end connections, TCP congestion control plays a critical role in order to not overflow the channel, although most of the network bandwidth bottlenecks are caused by the wireless systems. When TCP is coupled with high-delay channels, the protocol underperform; this is mainly due to long propagation delay, as it is the case with satellite links. To overcome the limitations of TCP on these links, various variants have been proposed, both rate-based or or burst-based. In this paper we present a cooperative transmission control that enhances the effectiveness of TCP asking only for a narrow senderside modification, operating exclusively at the access stage. It allows to boost throughput over high delay channels, increasing also fairness and friendliness between different TCP algorithms. After the description, we validate its effectiveness and show its properties by means of experimental results, derived from simulations performed on the ns-3 network simulator.

2015 - DyBRA: a Dynamic Bandwidth Reservation Algorithm to enhance Satellite Communications [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

In scenarios where a number of client nodes share a gateway in order to access a high-delay link, the original TCP as well as TCP variants specifically designed to improve performance on those links fail to provide optimal performance; this is due to the indirect inference of both end-to-end congestion and local channel conditions. To mitigate the former, C2ML (Congestion Control Middleware Layer) has been proposed as a tool for centralized and collaborative management of resources that can strongly improve performance for client hosts without affecting network resilience and connection survivability. To complete the picture, this paper proposes DyBRA, an improved version of C2ML with a bandwidth management algorithm designed to dynamically allocate bandwidth among client hosts on the basis of channel conditions, leading to improved performance regardless of the TCP variant employed by clients. Through simulations performed with the ns-3 network simulator, we show how DyBRA strongly improves throughput and TCP friendliness while reducing queue usage and latency.

2015 - Implementation and Validation of TCP Options and Congestion Control Algorithms for ns-3 [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

Currently, the ns-3 network simulator include rather limited TCP functionalities. TCP Options are not supported, and it misses models for widely used congestion control algorithms. Thus, simulations can be inadequate for today's standards and unable to represent what happen inside a broad range of networks, from Gigabit Ethernet to high-delay satellite channels. This paper presents an extension of the ns-3 TCP infrastructure, through the addition of the Window Scaling and the Timestamp Options as well as various models of TCP congestion control algorithms, from the widely used TCP Cubic to algorithms tailored for satellite or high Bandwidth-Delay Product links in general, namely TCP Hybla, Highspeed, Bic and Noordwijk. These additions are useful especially for research in high-speed or high-delay networks, filling the gap between real world and ns-3 TCP. Last but not least, this paper also presents some results regarding the validation of the added models, in order to demonstrate their correctness.

2015 - Integration of Satellite and LTE for Disaster Recovery [Articolo su rivista]
Casoni, Maurizio; Grazia, Carlo Augusto; Klapez, Martin; Patriciello, Natale; Amditis, Angelos; Sdongos, Evangelos
abstract

Wireless communications are critical for public protection and disaster relief (PPDR) professionals during the emergency operations that follow natural or man-made disasters, scenarios in which both commercial and dedicated terrestrial networks often fail to provide the necessary support. The reason is threefold: they simply get destroyed by the disaster, they cannot sustain the sudden surge of network demand or they fail to deliver the necessary bandwidth and/or other QoS guarantees. Because LTE is expected to become the main wireless technology for broadband communication, a lot of studies have been devoted to assess its compliance for PPDR purposes and to find suitable architectural solutions able to meet mission-critical requirements. This approach is surely worthy, but it is based on the assumption that infrastructure-based terrestrial systems are reliable. As a consequence, in worstcase emergency scenarios appropriate guarantees can be provided only in the hypothesis of huge investment costs. Recent developments in satellite technologies are bringing the availability of non-terrestrial high performance channels, with better properties when comparing to LTE for what regards availability and reliability. On this basis, the paper proposes a network architecture based on the integration of satellite and LTE networks for both infrastructure-based and infrastructure-less scenarios. The proposal aims to provide field operators and people in distress with transparent accessibility, coverage guarantees and broadband performance when terrestrial infrastructures are lacking, and to expand their coverage, capacity and resilience otherwise.

2015 - Performance Evaluation and Economic Modelling of PPDR Communication Systems [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale; Gierszal, H.; Tyczka, P.; Pawlina, K.; Amditis, A.; Sdongos, E.
abstract

Network-enabled services for public protection and disaster relief (PPDR) professionals have been more than necessary in today’s emergency situations. Under the extreme circumstances of an emergency, it is essential to have networks which support the required data throughput as well as high availability in spite of high traffic volume, and which minimize the end-to-end delay for applications: however, the choice between the existing technologies is not so easy for PPDR entities, given the high number of parameters associated to satisfying the stringent PPDR requirements,high investments required to permit desirable availability as well as modernization of the existing services (i.e. voice and data) and design constraints posed by network providers as current deployed network reach their boundaries when emergencies occur. This paper analyzes three different emergency scenarios and then presents a subset of the results obtained in terms of financial and economic recommendations, along with technical reports on throughput and end-toend delay.

2015 - PINK: Proactive INjection into acK, a queue manager to impose fair resource allocation among TCP flows [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

This paper presents preliminary work on PINK (Proactive INjection into acK), an AQM algorithm able to enhance TCP congestion control properties without dropping packets. PINK is a completely transparent solution that does not require any modification to the existing protocol stack of end hosts, and it is particularly suitable for high-delay PPDR systems. The algorithm is based on an explicit feedback scheme, able to enforce a fair bandwidth sharing among clients by modifying the Receive Window in TCP acknowledgements returning to them; such a feedback is computed for each flow, and it only needs the number of active connections, the flows RTTs and the shared link bandwidth. Therefore, PINK is a per-flow stateless AQM that works independently from the TCP algorithm used by clients, and it is fair regardless the flows RTTs, which is a key feature for PPDR systems. The effectiveness of the proposed algorithm is demonstrated using the ns-3 simulator.

2015 - QRM: A queue rate management for fairness and TCP flooding protection in mission-critical networks [Articolo su rivista]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

When statistical multiplexing is used to provide connectivity to a number of client hosts through a high-delay link, the original TCP as well as TCP variants designed to improve performance on those links often provide poor performance and sub-optimal QoS properties. Centralised and collaborative resource management tools like C2ML have been proposed to guarantee intra-protocol fairness, inter-protocol friendliness, low queues utilisation and optimal throughput along with the reliable delivery of packets. However, such tools offer only very limited security guarantees. Both good citizenship and security from flooding attacks are fundamental conditions for the provision of fairness, especially in mission-critical networks. For example, perpetrators of a man-provoked disaster may want to perform a resource exhaustion attack on the network supporting disaster recovery operations, so as to cut out legitimate users from the communications and increase the emergency impact. In this paper we present Queue Rate Management (QRM), an Active Queue Management scheme able to provide protection from traffic overflow attacks in scenarios where access to the shared link is controlled by a tool that assigns to client hosts a bandwidth upper bound. The proposed algorithm checks whether a node is exceeding its allowed rate, and consequently decides whether to keep or drop packets coming from that host. We mathematically prove that with QRM the gateway queue size can never exceed the Bandwidth-Delay Product of the channel. Furthermore, we employ the ns-3 network simulator to compare QRM with CoDel, RED and GREEN, showing how QRM provides better performance in terms of both throughput and QoS guarantees in the aforementioned scenarios.

2015 - Towards Emergency Networks Security with Per-Flow Queue Rate Management [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, Carlo Augusto; Klapez, Martin; Patriciello, Natale
abstract

When statistical multiplexing is used to provide connectivity to a number of client hosts through a high-delay link, the original TCP as well as TCP variants born to improve performance on those links often provide poor performance and sub-optimal QoS properties. To guarantee intra-protocol fairness, inter-protocol friendliness, low queues utilization and optimal throughput in mission-critical scenarios, Congestion Control Middleware Layer (C2ML) has been proposed as a tool for centralized and collaborative resource management. However, C2ML offers only very limited security guarantees. Because emergencies may be natural or man-provoked, in the latter case there may be interest to cut out legitimate users from the communication networks that support disaster recovery operations. In this paper we present Queue Rate Management (QRM), an Active Queue Management scheme able to provide protection from Resource Exhaustion Attacks in scenarios where access to the shared link is controlled by C2ML; the proposed algorithm checks whether a node is exceeding its allowed rate, and consequently decides whether to keep or drop packets coming from that node. We mathematically prove that with QRM the gateway queue size can never exceed the Bandwidth-Delay Product of the channel. Furthermore, we use the ns-3 simulator to compare QRM with CoDel and RED, showing how QRM provides better performance in terms of both throughput and QoS guarantees when employed with C2ML.

2014 - Integration between Terrestrial and Satellite Networks: the PPDR-TC vision [Relazione in Atti di Convegno]
Grazia, CARLO AUGUSTO; M., Klapez; N., Patriciello; Casoni, Maurizio; A., Amditis; E., Sdongos; H., Gierszal; D., Kanakidis; C., Katsigiannis; K., Romanowski; P., Simplicio; A., Oliveira; S., Sonander; J., Jackson
abstract

Wireless communication technologies are critical for public protection and disaster relief (PPDR) professionals during the emergency operations that follow natural or man-made disasters, scenarios in which commercial terrestrial networks often fail to provide the necessary support. The reason is threefold: they simply get disrupted by the disaster, they cannot sustain the sudden surge of network demand or they fail to deliver the necessary bandwidth and/or other QoS guarantees. In every PPDR operation reliable voice communications are critical, especially in the very early stages of the response; nevertheless, there is an increasing demand from the PPDR community for a wider range of data-centric services. While current technologies used for PPDR operations provide a rich set of voice-centric services, they are unable to sustain high-bandwidth data-oriented applications. As the PPDR-TC EU consortium, we propose a hybrid approach to tackle the question of determining the future architecture for Pan-European PPDR networks based on the integration of Terrestrial and Satellite technologies, presenting our first simulation results on the integration of LTE and Satellite Networks.

2014 - Reducing Latency in Satellite Emergency Networks through a Cooperative Transmission Control [Relazione in Atti di Convegno]
Casoni, Maurizio; Grazia, CARLO AUGUSTO; Klapez, Martin; Patriciello, Natale
abstract

The vast majority of efforts aimed to improve network performance are focused on the increase of application throughput. The same holds in the context of Emergency Networks, where operators ask for more bandwidth in order to exploit data-intensive services. Following a steady growth in network capacities and number of users, large buffers have been inserted all over the Internet. Their effects on networks are non-trivial: while they may effectively serve the purpose of exploiting the channel potential, they also create unnecessary delays by damaging the behavior of the most common transport protocol, TCP. Nevertheless, they are being assumed by new congestion control algorithms, especially those tailored for high-latency links such as satellite ones. According to the anywhere-anytime paradigm, these channels represents a key technology for both Emergency and General-Purpose networks. In this paper we first show how buffer lengths impact the perceived delay over satellite links that employ a recently proposed burst-based TCP protocol, and then present a cooperative transmission control that reduce buffers usage and latency while keeping high throughput and flow fairness, thus allowing for a better service provision through satellite links.