1,721,163 research outputs found
Leveraging network state for software-defined data centre network management
No full textThis work addresses key aspects in the management of a software-defined multi-tenant Data Centre Network (DCN). Software-defined networking (SDN) offers significant potential benefit for many aspects of DCN management – e.g. configuration, monitoring, performance and utilisation, and security – and many researchers have worked, successfully, over the last number of years to show how improvements to these areas could be achieved. The insight that motivated this work is that the focus by researchers and tool vendors has been on managing the current state or desired future state of the DCN. Meanwhile, issues relating to reviewing, analysing and evaluating the past state of a software-defined DCN have been neglected. SDN has been essential for DCNs to meet the requirements of a multi-tenant cloud environment - through automated, dynamic reconfiguration of network devices and services to accommodate tenants arriving, leaving, and modifying their resource requirements via a self-service interface. Consequently, a DCN operator cannot be expected to know the current state of the network, let alone past states, without tools to query the network and provide that information. DCN operators are well served by tools to manage and query the current state of an SDN, but not previous network states and events.
The research question addressed in this work is how to record the topological and configuration history of a DCN, present a useful view of that historical record to the DCN operator, and provide the means for the operator to query the historical DCN state. A related question is how to employ SDN itself to improve the performance of a software-defined DCN. Solving these issues is challenging because of the scale of a DCN (potentially scaling to hundreds of switches connecting thousands of devices), the constantly changing configuration of a multi-tenant software-defined DCN, and the duration of months or years over which the history must be recorded, analysed and available for querying.
The selected approach takes advantage of the decoupled nature of the control- and data-planes in SDN, to eavesdrop on communications between an SDN controller and switches. Emulated and conceptual models of a DCN have been created from key information extracted from the captured communications. The conceptual model relies on a combination of new and existing ontologies, with an extensible set of concepts and relationships that are the target of complex operator-focussed queries.
The contributions of the work are as follows:
1. Accurate reproduction of an emulated copy of a DCN (topology and state) for any time in its history solely from a passively captured log of control-plane messages.
2. The use of snapshots to speed up the reproduction time of an emulated DCN with topology and state for a particular point in time.
3. Use of an ontological approach to creating a temporal and topological model of a DCN, populated solely from a log of control-plane messages, and created for the purpose of answering operator queries.
4. A methodology to develop additional sophisticated queries against the ontological model regarding the historical state of and events on a DCN.
5. A method to improve the veracity of control-plane messages by reducing the latency of interactions between SDN controllers and hardware switches in a DCN
Software defined distributed cable networks: design and use cases
No full textCable networks have continuously evolved to enable new services and improve
infrastructure capabilities. Cable networks have recently witnessed a shift
from a centralized architecture to a distributed one to remain competitive by
supporting higher data rates. This shift complicates the management and
configuration of distributed network nodes in Distributed Access Architecture
(DAA). Hence, the development of new solutions to overcome this challenge
evolves as a crucial need for the success and economic deployment of DAA. In
the meantime, Software Defined Networking (SDN) technology evolved as a
novel networking paradigm that facilitates designing dynamic, cost-effective,
agile, centrally manageable, and programmable network architectures. SDN
segregates the data layer and control layer to enable the deployment of
centrally optimized operation of distributed network nodes.
This thesis focuses on developing a prototype for SDN-enabled DAA Cable
Networks. Specifically, an SDN agent was integrated with a legacy DAA remote
node to facilitate its communication with any SDN controller. Such integration
enables network applications deployed on top of the SDN controller to define
the forwarding behavior of these remote nodes. To illustrate this, two use
cases, namely Load Balancing and Failure Management, were deployed in the
Ryu controller. We validated the operation of these applications using a hybrid
setup that includes one physical/industrial remote DAA node with the rest of
the network emulated using the Mininet emulator. Additionally, we evaluate
the performance of the proposed load balancing and compare it to the no-load
balancing case using the web and video traffic. It’s clearly shown that load
balancing shows up to 6.4% of a performance improvement for video bitrate
without significantly impacting the web traffic.
The developed prototype could act as a precursor for designing and deploying
different use cases and the widespread adoption of SDN-based DAA networks
Wireless Sensor Networks, 6th European Conference, EWSN 2009, Cork, Ireland, February 11-13, 2009. Proceedings
No full textContent-aware compression for big textual data analysis
No full textA substantial amount of information on the Internet is present in the form of text. The value of this semi-structured and unstructured data has been widely acknowledged, with consequent scientific and commercial exploitation. The ever-increasing data production, however, pushes data analytic platforms to their limit. This thesis proposes techniques for more efficient textual big data analysis suitable for the Hadoop analytic platform. This research explores the direct processing of compressed textual data. The focus is on developing novel compression methods with a number of desirable properties to support text-based big data analysis in distributed environments. The novel contributions of this work include the following. Firstly, a Content-aware Partial Compression (CaPC) scheme is developed. CaPC makes a distinction between informational and functional content in which only the informational content is compressed. Thus, the compressed data is made transparent to existing software libraries which often rely on functional content to work. Secondly, a context-free bit-oriented compression scheme (Approximated Huffman Compression) based on the Huffman algorithm is developed. This uses a hybrid data structure that allows pattern searching in compressed data in linear time. Thirdly, several modern compression schemes have been extended so that the compressed data can be safely split with respect to logical data records in distributed file systems. Furthermore, an innovative two layer compression architecture is used, in which each compression layer is appropriate for the corresponding stage of data processing. Peripheral libraries are developed that seamlessly link the proposed compression schemes to existing analytic platforms and computational frameworks, and also make the use of the compressed data transparent to developers. The compression schemes have been evaluated for a number of standard MapReduce analysis tasks using a collection of real-world datasets. In comparison with existing solutions, they have shown substantial improvement in performance and significant reduction in system resource requirements
Baran: a service-oriented cloud-based user monitoring and data analysis framework
Get PDFMost humans now live in an age of connected digital devices where their interactions with these devices are recorded in a number of ways, by different organisations, under various levels of user control. A user is often unaware of how much data they create, of where the data resides, and of how their data is used. It is challenging for a user to inspect all this personal data, to control the storage and use of the data, and to exploit the data for their benefit in a safe way. These are the challenges that this thesis addresses. The focus is on the user’s digital trail of information – i.e. the record of user interactions and associated context information from the digital devices associated with the user. The digital devices associated with a user, and with which they interact, might include smartphones, laptops, smart watches, fitness bands, and smart household appliances. The thesis develops a conceptual model and extensible data structure, called the UDI (User Digital Imprint), which accommodates a variety of digital data from digital devices along with information derived from that data. A software framework, Baran, is developed that implements the UDI and provides services that support the gathering, management and analysis of the user data. The Baran framework allows the user to inspect and analyse their data and supports (under user control) the sharing of the data in order that assistive services for the user can be provided by 3rd parties. The framework is cloud-based and service-oriented, enabling the framework to make use of external services (e.g. machine learning services) and to provide services for external entities (e.g. supplying some subset of user data to a smart coffee maker). Thus, Baran can be extended with both user services and external services, where the sharing of user data with external entities is directly under user control on a per-use basis. By gathering, analysing and making available comprehensive information about a user’s digital interactions, Baran also enables study of aspects of User Experience (UX), as might be of interest to UX researchers or product designers. Three case studies are presented to demonstrate aspects of Baran and how it can be used in different scenarios. Rather than a limited-scope, specific solution (such as recent functionality introduced by Google and Apple) Baran provides a general extensible framework that covers a range of user digital interactions on a variety of devices, and enables a wide range of applications, where all data sharing is under explicit user control
Improving video streaming experience through network measurements and analysis
Get PDFMultimedia traffic dominates today’s Internet. In particular, the most prevalent traffic carried over wired and wireless networks is video. Most popular streaming providers (e.g. Netflix, Youtube) utilise HTTP adaptive streaming (HAS) for video content delivery to end-users. The power of HAS lies in the ability to change video quality in real time depending on the current state of the network (i.e. available network resources). The main goal of HAS algorithms is to maximise video quality while minimising re-buffering events and switching between different qualities. However, these requirements are opposite in nature, so striking a perfect blend is challenging, as there is no single widely accepted metric that captures user experience based on the aforementioned requirements. In recent years, researchers have put a lot of effort into designing subjectively validated metrics that can be used to map quality, re-buffering and switching behaviour of HAS players to the overall user experience (i.e. video QoE). This thesis demonstrates how data analysis can contribute in improving video QoE. One of the main characteristics of mobile networks is frequent throughput fluctuations. There are various underlying factors that contribute to this behaviour, including rapid changes in the radio channel conditions, system load and interaction between feedback loops at the different time scales. These fluctuations highlight the challenge to achieve a high video user experience. In this thesis, we tackle this issue by exploring the possibility of throughput prediction in cellular networks. The need for better throughput prediction comes from data-based evidence that standard throughput estimation techniques (e.g. exponential moving average) exhibit low prediction accuracy. Cellular networks deploy opportunistic exponential scheduling algorithms (i.e. proportional-fair) for resource allocation among mobile users/devices. These algorithms take into account a user’s physical layer information together with throughput demand. While the algorithm itself is proprietary to the manufacturer, physical layer and throughput information are exchanged between devices and base stations. Availability of this information allows for a data-driven approach for throughput prediction. This thesis utilises a machine-learning approach to predict available throughput based on measurements in the near past. As a result, a prediction accuracy with an error less than 15% in 90% of samples is achieved. Adding information from other devices served by the same base station (network-based information) further improves accuracy while lessening the need for a large history (i.e. how far to look into the past). Finally, the throughput prediction technique is incorporated to state-of-the-art HAS algorithms. The approach is validated in a commercial cellular network and on a stock mobile device. As a result, better throughput prediction helps in improving user experience up to 33%, while minimising re-buffering events by up to 85%. In contrast to wireless networks, channel characteristics of the wired medium are more stable, resulting in less prominent throughput variations. However, all traffic traverses through network queues (i.e. a router or switch), unlike in cellular networks where each user gets a dedicated queue at the base station. Furthermore, network operators usually deploy a simple first-in-first-out queuing discipline at queues. As a result, traffic can experience excessive delays due to the large queue sizes, usually deployed in order to minimise packet loss and maximise throughput. This effect, also known as bufferbloat, negatively impacts delay-sensitive applications, such as web browsing and voice. While there exist guidelines for modelling queue size, there is no work analysing its impact on video streaming traffic generated by multiple users. To answer this question, the performance of multiple videos clients sharing a bottleneck link is analysed. Moreover, the analysis is extended to a realistic case including heterogeneous round-trip-time (RTT) and traffic (i.e. web browsing). Based on experimental results, a simple two queue discipline is proposed for scheduling heterogeneous traffic by taking into account application characteristics. As a result, compared to the state-of-the-art Active Queue Management (AQM) discipline, Controlled Delay Management (CoDel), the proposed discipline decreases median Page Loading Time (PLT) of web traffic by up to 80% compared to CoDel, with no significant negative impact on video QoE
Repairing wireless sensor network connectivity in damaged environments
No full textA wireless sensor network can become partitioned due to node failure, requiring the deployment of additional relay nodes in order to restore network connectivity. This introduces an optimisation problem involving a tradeoff between the number of additional nodes that are required and the costs of moving through the sensor field for the purpose of node placement. This tradeoff is application-dependent, influenced for example by the relative urgency of network restoration. In addition, minimising the number of relay nodes might lead to long routing paths to the sink, which may cause problems of data latency. This data latency is extremely important in wireless sensor network applications such as battlefield surveillance, intrusion detection, disaster rescue, highway traffic coordination, etc. where they must not violate the real-time constraints. Therefore, we also consider the problem of deploying multiple sinks in order to improve the network performance. Previous research has only parts of this problem in isolation, and has not properly considered the problems of moving through a constrained environment or discovering changes to that environment during the repair or network quality after the restoration. In this thesis, we firstly consider a base problem in which we assume the exploration tasks have already been completed, and so our aim is to optimise our use of resources in the static fully observed problem. In the real world, we would not know the radio and physical environments after damage, and this creates a dynamic problem where damage must be discovered. Therefore, we extend to the dynamic problem in which the network repair problem considers both exploration and restoration. We then add a hop-count constraint for network quality in which the desired locations can talk to a sink within a hop count limit after the network is restored. For each new problem of the network repair, we have proposed different solutions (heuristics and/or complete algorithms) which prioritise different objectives. We evaluate our solutions based on simulation, assessing the quality of solutions (node cost, movement cost, computation time, and total restoration time) by varying the problem types and the capability of the agent that makes the repair. We show that the relative importance of the objectives influences the choice of algorithm, and different speeds of movement for the repairing agent have a significant impact on performance, and must be taken into account when selecting the algorithm. In particular, the node-based approaches are the best in the node cost, and the path-based approaches are the best in the mobility cost. For the total restoration time, the node-based approaches are the best with a fast moving agent while the path-based approaches are the best with a slow moving agent. For a medium speed moving agent, the total restoration time of the node-based approaches and that of the path-based approaches are almost balanced
Efficient delivery of scalable media streaming over lossy networks
No full textRecent years have witnessed a rapid growth in the demand for streaming video over the Internet, exposing challenges in coping with heterogeneous device capabilities and varying network throughput. When we couple this rise in streaming with the growing number of portable devices (smart phones, tablets, laptops) we see an ever-increasing demand for high-definition videos online while on the move. Wireless networks are inherently characterised by restricted shared bandwidth and relatively high error loss rates, thus presenting a challenge for the efficient delivery of high quality video. Additionally, mobile devices can support/demand a range of video resolutions and qualities. This demand for mobile streaming highlights the need for adaptive video streaming schemes that can adjust to available bandwidth and heterogeneity, and can provide us with graceful changes in video quality, all while respecting our viewing satisfaction. In this context the use of well-known scalable media streaming techniques, commonly known as scalable coding, is an attractive solution and the focus of this thesis. In this thesis we investigate the transmission of existing scalable video models over a lossy network and determine how the variation in viewable quality is affected by packet loss. This work focuses on leveraging the benefits of scalable media, while reducing the effects of data loss on achievable video quality. The overall approach is focused on the strategic packetisation of the underlying scalable video and how to best utilise error resiliency to maximise viewable quality. In particular, we examine the manner in which scalable video is packetised for transmission over lossy networks and propose new techniques that reduce the impact of packet loss on scalable video by selectively choosing how to packetise the data and which data to transmit. We also exploit redundancy techniques, such as error resiliency, to enhance the stream quality by ensuring a smooth play-out with fewer changes in achievable video quality. The contributions of this thesis are in the creation of new segmentation and encapsulation techniques which increase the viewable quality of existing scalable models by fragmenting and re-allocating the video sub-streams based on user requirements, available bandwidth and variations in loss rates. We offer new packetisation techniques which reduce the effects of packet loss on viewable quality by leveraging the increase in the number of frames per group of pictures (GOP) and by providing equality of data in every packet transmitted per GOP. These provide novel mechanisms for packetizing and error resiliency, as well as providing new applications for existing techniques such as Interleaving and Priority Encoded Transmission. We also introduce three new scalable coding models, which offer a balance between transmission cost and the consistency of viewable quality
Planning the deployment of fault-tolerant wireless sensor networks
No full textSince Wireless Sensor Networks (WSNs) are subject to failures, fault-tolerance becomes an
important requirement for many WSN applications. Fault-tolerance can be enabled in
different areas of WSN design and operation, including the Medium Access Control (MAC)
layer and the initial topology design. To be robust to failures, a MAC protocol must be able
to adapt to traffic fluctuations and topology dynamics. We design ER-MAC that can switch
from energy-efficient operation in normal monitoring to reliable and fast delivery for
emergency monitoring, and vice versa. It also can prioritise high priority packets and
guarantee fair packet deliveries from all sensor nodes.
Topology design supports fault-tolerance by ensuring that there are alternative acceptable
routes to data sinks when failures occur. We provide solutions for four topology planning
problems: Additional Relay Placement (ARP), Additional Backup Placement (ABP),
Multiple Sink Placement (MSP), and Multiple Sink and Relay Placement (MSRP). Our
solutions use a local search technique based on Greedy Randomized Adaptive Search
Procedures (GRASP). GRASP-ARP deploys relays for (k,l)-sink-connectivity, where each
sensor node must have k vertex-disjoint paths of length ≤ l. To count how many disjoint
paths a node has, we propose Counting-Paths. GRASP-ABP deploys fewer relays than
GRASP-ARP by focusing only on the most important nodes – those whose failure has the
worst effect. To identify such nodes, we define Length-constrained Connectivity and
Rerouting Centrality (l-CRC). Greedy-MSP and GRASP-MSP place minimal cost sinks to
ensure that each sensor node in the network is double-covered, i.e. has two length-bounded
paths to two sinks. Greedy-MSRP and GRASP-MSRP deploy sinks and relays with minimal
cost to make the network double-covered and non-critical, i.e. all sensor nodes must have
length-bounded alternative paths to sinks when an arbitrary sensor node fails. We then
evaluate the fault-tolerance of each topology in data gathering simulations using ER-MAC
A Quality of Service framework for upstream traffic in LTE across an XG-PON backhaul
Get PDFPassive Optical Networks (PON) are promising as a transport network technology due to the high network capacity, long reach and strong QoS support in the latest PON standards. Long Term Evolution (LTE) is a popular wireless technology for its large data rates in the last mile. The natural integration of LTE and XG-PON, which is one of the latest standards of PON, presents several challenges for XG-PON to satisfy the backhaul QoS requirements of aggregated upstream LTE applications. This thesis proves that a dedicated XG-PON-based backhaul is capable of ensuring the QoS treatment required by different upstream application types in LTE, by means of standard-compliant Dynamic Bandwidth Allocation (DBA) mechanisms. First the design and evaluation of a standard-compliant, robust and fast XG-PON simulation module developed for the state-of-the-art ns-3 network simulator is presented in the thesis. This XG-PON simulation module forms a trustworthy and large-scale simulation platform for the evaluations in the rest of the thesis, and has been released for use by the scientific community. The design and implementation details of the XGIANT DBA, which provides standard complaint QoS treatment in an isolated XG-PON network, are then presented in the thesis along with comparative evaluations with the recently-published EBU DBA. The evaluations explored the ability of both XGIANT and EBU in terms of queuing-delay and throughput assurances for different classes of simplified (deterministic) traffic models, for a range of upstream loading in XG-PON. The evaluation of XGIANT and EBU DBAs are then presented for the context of a dedicated XG-PON backhaul in LTE with regard to the influence of standard-compliant and QoS-aware DBAs on the performance of large-scale, UDP-based applications. These evaluations disqualify both XGIANT and EBU DBAs in providing prioritised queuing delay performances for three upstream application types (conversational voice, peer-to-peer video and best-effort Internet) in LTE; the evaluations also indicate the need to have more dynamic and efficient QoS policies, along with an improved fairness policy in a DBA used in the dedicated XG-PON backhaul to ensure the QoS requirements of the upstream LTE applications in the backhaul. Finally, the design and implementation details of two standard-compliant DBAs, namely Deficit XGIANT (XGIANT-D) and Proportional XGIANT (XGIANT-P), which provide the required QoS treatment in the dedicated XG-PON backhaul for all three application types in the LTE upstream are presented in the thesis. Evaluations of the XGIANT-D and XGIANT-P DBAs presented in the thesis prove the ability of the fine-tuned QoS and fairness policies in the DBAs in ensuring prioritised and fair queuing-delay and throughput efficiency for UDP- and TCP-based applications, generated and aggregated based on realistic conditions in the LTE upstream
- …
