The usage of smartphones has been increasing with surprising speed. These smartphones are popular for delivery of video content. The main drawbacks of these smartphones are battery life and video freezing. Despite, while streaming a video it consumes large of amount of power affecting QoE. So, in this case we considered streaming a video from server to mobile client involving ONOFF characteristics. While streaming, there exists some transition delay while switching the power states and the effect of these transition delays might affect instantaneous power consumption of the smartphone. Henceforth, this thesis aims to determine the effect on instantaneous power consumption from distributed state durations and transitions in exponential fluid flow model, for a streamed video. Power measurements along with ON and OFF times were measured with the help of a benchmark tool, Monsoon Power Monitor tool. VLQoE tool, a video streaming tool was used to present a two state model based on the inter-picture time, for the HTTP-based video streaming. Experiments were executed in a closed enclosure setup using a black-box to avoid external obstacles that might possibly affect the power consumption metrics. Considering these measurements, the effect on instantaneous power consumption stemming from the exponentially distributed state durations and transitions in the corresponding fluid flow model can be determined and modelled.

With the increase in demand for video streaming services on the hand held mobile terminals with limited battery life, it is important to maintain the user Quality of Experience (QoE) while taking the resource consumption into consideration. Hence, the goal is to offer as good quality as feasible, avoiding as much user-annoyance as possible. Hence, it is essential to deliver the video, avoiding any uncontrollable quality distortions. This can be possible when an optimal (or desirable) throughput value is chosen such that exceeding the particular threshold results in entering a region of unstable QoE, which is not feasible. Hence, the concept of QoE-aware sustainable throughput is introduced as the maximal value of the desirable throughput that avoids disturbances in the Quality of Experience (QoE) due to delivery issues, or keeps them at an acceptable minimum. The thesis aims at measuring the sustainable throughput values when video streams of different resolutions are streamed from the server to a mobile client over wireless links, in the presence of network disturbances packet loss and delay. The video streams are collected at the client side for quality assessment and the maximal throughput at which the QoE problems can still be kept at a desired level is determined. Scatter plots were generated for the individual opinion scores and their corresponding throughput values for the disturbance case and regression analysis is performed to find the best fit for the observed data. Logarithmic, exponential, linear and power regressions were considered in this thesis. The R-squared values are calculated for each regression model and the model with R-squared value closest to 1 is determined to be the best fit. Power regression model and logarithmic model have the R-squared values closest to 1.  Better quality ratings have been observed for the low resolution videos in the presence of packet loss and delay for the considered test cases. It can be observed that the QoE disturbances can be kept at a desirable level for the low resolution videos and from the test cases considered for the investigation, 360px video is more resilient in case of high delay and packet loss values and has better opinion score values. Hence, it can be observed that the throughput is sustainable at this threshold.

Today, distributed applications run at data centre and Internet scales, from intensive data analysis, such as MapReduce; to the dynamic demands of a worldwide audience, such as YouTube. The network is essential to these applications at both scales. To provide adequate support, we must understand the full requirements of the applications, which are revealed by the workloads. In this thesis, we study distributed system applications at different scales to enrich this understanding. Large-scale Internet applications have been studied for years, such as social networking service (SNS), video on demand (VoD), and content delivery networks (CDN). An emerging type of video broadcasting on the Internet featuring crowdsourced live video streaming has garnered attention allowing platforms such as Twitch to attract over 1 million concurrent users globally. To better understand Twitch, we collected real-time popularity data combined with metadata about the contents and found the broadcasters rather than the content drives its popularity. Unlike YouTube and Netflix where content can be cached, video streaming on Twitch is generated instantly and needs to be delivered to users immediately to enable real-time interaction. Thus, we performed a large-scale measurement of Twitchs content location revealing the global footprint of its infrastructure as well as discovering the dynamic stream hosting and client redirection strategies that helped Twitch serve millions of users at scale. We next consider applications that run inside the data centre. Distributed computing applications heavily rely on the network due to data transmission needs and the scheduling of resources and tasks. One successful application, called Hadoop, has been widely deployed for Big Data processing. However, little work has been devoted to understanding its network. We found the Hadoop behaviour is limited by hardware resources and processing jobs presented. Thus, after characterising the Hadoop traffic on our testbed with a set of benchmark jobs, we built a simulator to reproduce Hadoops job traffic With the simulator, users can investigate the connections between Hadoop traffic and network performance without additional hardware cost. Different network components can be added to investigate the performance, such as network topologies, queue policies, and transport layer protocols. In this thesis, we extended the knowledge of networking by investigated two widelyused applications in the data centre and at Internet scale. We (i) studied the most popular live video streaming platform Twitch as a new type of Internet-scale distributed application revealing that broadcaster factors drive the popularity of such platform, and we (ii) discovered the footprint of Twitch streaming infrastructure and the dynamic stream hosting and client redirection strategies to provide an in-depth example of video streaming delivery occurring at the Internet scale, also we (iii) investigated the traffic generated by a distributed application by characterising the traffic of Hadoop under various parameters, (iv) with such knowledge, we built a simulation tool so users can efficiently investigate the performance of different network components under distributed application.

Over the last decade, live video streaming applications have gained great popularity among users but put great pressure on video servers and the Internet. In order to satisfy the growing demands for live video streaming, Peer-to-Peer(P2P) has been developed to relieve the video servers of bandwidth bottlenecks and computational load. Furthermore, Network Coding (NC) has been proposed and proved as a significant breakthrough in information theory and coding theory. According to previous research, NC not only brings substantial improvements regarding throughput and delay in data transmission, but also provides innovative solutions for multiple issues related to resource allocation, such as the coupon-collection problem, allocation and scheduling procedure. However, the complex NC-driven P2P streaming network poses substantial challenges to the packet scheduling algorithm. This thesis focuses on the packet scheduling algorithm for video multicast in NC-driven P2P streaming network. It determines how upload bandwidth resources of peer nodes are allocated in different transmission scenarios to achieve a better Quality of Service(QoS). First, an optimized rate allocation algorithm is proposed for scalable video transmission (SVT) in the NC-based lossy streaming network. This algorithm is developed to achieve the tradeoffs between average video distortion and average bandwidth redundancy in each generation. It determines how senders allocate their upload bandwidth to different classes in scalable data so that the sum of the distortion and the weighted redundancy ratio can be minimized. Second, in the NC-based non-scalable video transmission system, the bandwidth ineffi- ciency which is caused by the asynchronization communication among peers is reduced. First, a scalable compensation model and an adaptive push algorithm are proposed to reduce the unrecoverable transmission caused by network loss and insufficient bandwidth resources. Then a centralized packet scheduling algorithm is proposed to reduce the unin- formative transmission caused by the asynchronized communication among sender nodes. Subsequently, we further propose a distributed packet scheduling algorithm, which adds a critical scalability property to the packet scheduling model. Third, the bandwidth resource scheduling for SVT is further studied. A novel multiple- generation scheduling algorithm is proposed to determine the quality classes that the receiver node can subscribe to so that the overall perceived video quality can be maxi- mized. A single generation scheduling algorithm for SVT is also proposed to provide a faster and easier solution to the video quality maximization function. Thorough theoretical analysis is conducted in the development of all proposed algorithms, and their performance is evaluated via comprehensive simulations. We have demon- strated, by adjusting the conventional transmission model and involving new packet scheduling models, the overall QoS and bandwidth efficiency are dramatically improved. In non-scalable video streaming system, the maximum video quality gain can be around 5dB compared with the random push method, and the overall uninformative transmiss- sion ratio are reduced to 1% - 2%. In scalable video streaming system, the maximum video quality gain can be around 7dB, and the overall uninformative transmission ratio are reduced to 2% - 3%.

The transmitting of video content over Vehicular Ad Hoc Networks (VANETs) faces a great number of challenges caused by strict QoS (Quality of Service) requirements and highly dynamic network topology. In order to tackle these challenges, multipath forwarding schemes can be regarded as potential solutions. However, route coupling effect and the path length growth severely impair the performance of multipath schemes. In this thesis, the current research status about video streaming over VANETs as well as multipath transmissions are reviewed. With the demand to discover a more suitable solution, we propose the Location-Aware Multipath Video Streaming (LIAITHON+) protocol to address video streaming over urban VANETs. LIAITHON+ uses location information to discover relatively short paths with minimal route coupling effect. The performance results have shown it outperforms the underlying single path solution as well as the node-disjoint multipath solution. In addition, the impact of added redundancy on the multipath solution is investigated through LIAITHON+. According to the results, added redundancy has a different impact depending on the data rate.

The integration of heterogeneous access networks is becoming a possible feature of 4G wireless networks. It is challenging to deliver the multimedia services over such integrated networks because of the discrepancy in the bandwidth of different networks. This thesis presents an adaptive approach that combines source rate adaptation and buffering to achieve high quality VBR video streaming with less quality variation over an integrated two-tier network. Statistical information of the residence time in each network or localization information are utilized to anticipate the handoff occurrence. The performance of this approach is analyzed under the CBR case using a Markov reward model. Simulation under the CBR and VBR cases is conducted for different types of network models. The results are compared with a dynamic programming algorithm as well as other naive or intuitive algorithms, and proved to be promising.

The integration of heterogeneous access networks is becoming a possible feature of 4G wireless networks. It is challenging to deliver the multimedia services over such integrated networks because of the discrepancy in the bandwidth of different networks. This thesis presents an adaptive approach that combines source rate adaptation and buffering to achieve high quality VBR video streaming with less quality variation over an integrated two-tier network. Statistical information of the residence time in each network or localization information are utilized to anticipate the handoff occurrence. The performance of this approach is analyzed under the CBR case using a Markov reward model. Simulation under the CBR and VBR cases is conducted for different types of network models. The results are compared with a dynamic programming algorithm as well as other naive or intuitive algorithms, and proved to be promising.

The emerging vehicular ad-hoc networks (VANETs) offer a variety of applications and new potential markets related to safety, convenience and entertainment, however, they suffer from a number of challenges not shared so deeply by other types of existing networks, particularly, in terms of mobility of nodes, and end-to-end quality of service (QoS) provision. Although several existing works in the literature have attempted to provide efficient protocols at different layers targeted mostly for safety applications, there remain many barriers to be overcome in order to constrain the widespread use of such networks for non-safety applications, specifically, for video streaming: 1) impact of high speed mobility of nodes on end-to-end QoS provision; 2) cross-layer protocol design while keeping low computational complexity; 3) considering customer-oriented QoS metrics in the design of protocols; and 4) maintaining seamless single-hop and multi-hop connection between the destination vehicle and the road side unit (RSU) while network is moving. This thesis addresses each of the above limitations in design of cross-layer protocols for video streaming application. 1) An adaptive MAC retransmission limit selection scheme is proposed to improve the performance of IEEE 802.11p standard MAC protocol for video streaming applications over VANETs. A multi-objective optimization framework, which jointly minimizes the probability of playback freezes and start-up delay of the streamed video at the destination vehicle by tuning the MAC retransmission limit with respect to channel statistics as well as packet transmission rate, is applied at road side unit (RSU). Two-hop transmission is applied in zones in which the destination vehicle is not within the transmission range of any RSU. In the multi-hop scenario, we discuss the computation of access probability used in the MAC adaptation scheme and propose a cross-layer path selection scheme; 2) We take advantage of similarity between multi-hop urban VANETs in dense traffic conditions and mesh connected networks. First, we investigate an application-centric routing scheme for video streaming over mesh connected overlays. Next, we introduce the challenges of urban VANETs compared to mesh networks and extend the proposed scheme in mesh network into a protocol for urban VANETs. A classification-based method is proposed to select an optimal path for video streaming over multi-hop mesh networks. The novelty is to translate the path selection over multi-hop networks to a standard classification problem. The classification is based on minimizing average video packet distortion at the receiving nodes. The classifiers are trained offline using a vast collection of video sequences and wireless channel conditions in order to yield optimal performance during real time path selection. Our method substantially reduces the complexity of conventional exhaustive optimization methods and results in high quality (low distortion). Next, we propose an application-centric routing scheme for real-time video transmission over urban multi-hop vehicular ad-hoc network (VANET) scenarios. Queuing based mobility model, spatial traffic distribution and prob- ability of connectivity for sparse and dense VANET scenarios are taken into consideration in designing the routing protocol. Numerical results demonstrate the gain achieved by the proposed routing scheme versus geographic greedy forwarding in terms of video frame distortion and streaming start-up delay in several urban communication scenarios for various vehicle entrance rate and traffic densities; and 3) finally, the proposed quality-driven routing scheme for delivering video streams is combined with a novel IP management scheme. The routing scheme aims to optimize the visual quality of the transmitted video frames by minimizing the distortion, the start-up delay, and the frequency of the streaming freezes. As the destination vehicle is in motion, it is unrealistic to assume that the vehicle will remain connected to the same access router (AR) for the whole trip. Mobile IP management schemes can benefit from the proposed multi-hop routing protocol in order to adapt proxy mobile IPv6 (PMIPv6) for multi-hop VANET for video streaming applications. The proposed cross-layer protocols can significantly improve the video streaming quality in terms of the number of streaming freezes and start-up delay over VANETs while achieving low computational complexity by using pattern classification methods for optimization.

While the demand for video streaming services has risen rapidly in recent years, supporting video streaming service to a large number of receivers still remains a challenging task. Issues of video streaming in the Internet, such as scalability, and reliability are still under extensive research. Recently proposed network contexts such as overlay networks, and mobile ad hoc networks pose even tougher challenges. This thesis focuses on supporting scalable video streaming applications under various network environments. More specifically, this thesis investigates the following problems: i) Server selection in replicated batching video on demand (VoD) systems: we find out that, to optimize the user perceived latency, it is vital to consider the server state information and channel allocation schemes when making server selection decisions. We develop and evaluate a set of server selection algorithms that use increasingly more information. ii) Scalable live video streaming with time shifting and video patching: we consider the problem of how to enable continuous live video streaming to a large group of clients in cooperative but unreliable overlay networks. We design a server-based architecture which uses a combined technique of time-shifting video server and P2P video patching. iii) A Cooperative patching architecture in overlay networks: We design a cooperative patching architecture which shifts video patching responsibility completely to the client side. An end-host retrieves lost data from other end-hosts within the same multicast group. iv) V3: a vehicle to vehicle video streaming architecture: We propose V3, an architecture to provide live video streaming service to driving vehicles through vehicle-to-vehicle (V2V) networks. V3 incorporates a novel signaling mechanism to continuously trigger video sources to send video data back to the receiver. It also adopts a store-carry-and-forward approach to transmit video data in a partitioned network environment. We also develop a multicasting framework that enables live video streaming applications from multiple sources to multiple receivers in V2V networks. A message integration scheme is used to suppress the signaling overhead, and a two-level tree-based routing approach is adopted to forward the video data.

This thesis demonstrates the performance of Probabilistic Early Response TCP (PERT), a new TCP congestion control, for video streaming. As a delay based protocol, it measures the delay at the end host and adjusts the congestion window accordingly. Our experiments show that PERT improves video delivery performance by decreasing the fraction of packets delivered late. Furthermore, our Linux live streaming test indicates that PERT is able to reduce the playback glitches, when high resolution video is delivered over a link with non-zero packet loss. In order to operate PERT at higher thoughputs, we design PERT to work with Acknowledgement (ACK) coalescing at the receiver. ACK coalescing makes data transfers burstier and makes it hard to estimate delays accurately. We apply TCP pacing to fix this issue, and validate its effectiveness in the aspects of throughput, packet loss and fairness. Our experiment results also show that PERT with Delayed ACK and Pacing is more friendly, and therefore more suitable when multiple traffic flows are competing for limited bottleneck bandwidth or sharing the same router buffer.