Guaranteeing QoS of media-based applications in virtualized environment

In an Ethernet Passive Optical Network (EPON) a variety of applications with different Quality of Services (QoS) should be transmitted. Therefore, an EPON network must provide a differentiated QoS for different applications in such a way that the utilization of upstream channel should not go down. In this paper, we shall propose a new Dynamic Bandwidth Allocation (DBA) called MHPP (Maximum High Priority Proportion) to reduce packet loss rate and packet delay for high priority traffic. MHPP first grants those Optical Network Units (ONUs) that have more high priority traffic in their granted bits. Hence, the order of ONUs is changed in every transmission cycle based on the proportion of high priority data to granted bits. Our performance evaluations show that the MHPP algorithm can significantly reduce packet delay and packet loss for high priority traffic.

Efficient and reliable bandwidth allocation remains an important open issue in the management of networks that aim to offer a guaranteed quality of service (QoS). Guaranteeing QoS to incoming requests means that users explicitly specify certain requirements such as throughput, loss or delay. It also means that the provider needs to be prepared to compensate for transient outages or overloads and re-allocate resources according to priorities. Dynamic bandwidth allocation can be used to assure that high priority requests can be always routed through relatively favorable paths within a differentiated services environment. In this paper we introduce a utility-based QoS model and a generalized bandwidth allocation scheme which accounts for the users of QoS requirements. We analyze the dynamic and static bandwidth allocation policies in the presence of four types of traffic each described with its utility value when the network experiences overloads. Our approach allows a service provider to differentiate between different types of customers based on their priority or the service charges that they pay, in order to offer real time services, to provide QoS guarantees for multimedia traffic and to guarantee stability even in overloaded conditions.

Integrating QoS awareness with virtualization in cloud computing systems for delay-sensitive applications

A virtualized cloud platform may host several cloud services/applications simultaneously. Each hosted cloud service usually runs on a virtual cluster, consisting of several virtual machines (VMs) with a virtual network. In many cases, the virtual clusters share the overall physical network bandwidth. Thus, the quality of the cloud services sharing the same physical networks can be seriously affected when one of the cloud services produces a high traffic load. In this paper, we propose a mechanism to solve the mentioned issue. The proposed mechanism utilizes a logically centralized QoS controller to allocate network bandwidth to virtual clusters dynamically. The QoS controller uses a monitor to continuously gather network usage of each VM, and calculates the bandwidth consumption in the granule of virtual clusters. A Rate Limiter is bundled to each physical machine for triggering bandwidth re-distribution. The proposed mechanism is implemented on the OpenStack-based cloud platform, SAMEVED, which is developed to support on-line network security experiments. We implemented several network bandwidth re-distribution strategies on the proposed mechanism. We emulate the real network flows in the platform, and the experiment results show that, the proposed approach can effectively reduce nearly one third of packet loss rate when running a video streaming service in a high network traffic scenario.

The relationship between the user perceived Quality of Experience (QoE) with Internet applications and the Quality of Service (QoS) of the underlying network and applications is complex. Unveiling statistical relations between QoE and QoS can boost the prediction and diagnosis of QoE. In this paper, we shed light on the relationship between QoE and QoS for a popular application: YouTube video streaming. We conducted a controlled study where we asked users to rate their perceived quality of YouTube videos under different network conditions. During this experiments, we also captured network QoS and application QoS. We then analyze the resulting dataset with SES, a feature selection algorithm that identifies multiple, minimal-size, statistically-equivalent signatures with maximal predictive power for a target variable (e.g., QoE). We found that we can build optimal QoE predictors using a minimal signature of only three features from application or network QoS metrics compared to four when we consider features from both layers.

HTTP video streaming, such as Flash video, is widely deployed to deliver stored media. Owing to TCP's reliable service, the picture and sound quality would not be degraded by network impairments, such as high delay and packet loss. However, the network impairments can cause rebuffering events which would result in jerky playback and deform the video's temporal structure. These quality degradations could adversely affect users' quality of experience (QoE). In this paper, we investigate the relationship among three levels of quality of service (QoS) of HTTP video streaming: network QoS, application QoS, and user QoS (i.e., QoE). Our ultimate goal is to understand how the network QoS affects the QoE of HTTP video streaming. Our approach is to first characterize the correlation between the application and network QoS using analytical models and empirical evaluation. The second step is to perform subjective experiments to evaluate the relationship between application QoS and QoE. Our analysis reveals that the frequency of rebuffering is the main factor responsible for the variations in the QoE.

Fuzzy logic based dynamic wavelength and bandwidth allocation for 5G front haul networks

Broadband Wireless Access (BWA) network such as LTE brings heterogeneity in terms of different radio access technologies, multi-tier architectures and co-implementation of various protocols to support various types of services with desired Quality of Service (QoS) for the subscribers. However, due to limited bandwidth and high demand of LTE-BWA networks, effective network planning is required to utilize the available radio resources in an efficient way. To achieve this target, this paper aims to implement a unique Radio Resource Management scheme for a heterogeneous LTE based BWA network (BWA Het-Nets) which consists of Small cells along with Macro cells. The proposed analysis has two components: (1) Received Signal Strength (RSS) based CAC policy; and (2) Dynamic Bandwidth Allocation (DBA) scheme for QoS provisioning. The novelty of this work lies on the integration of the RSS based CAC policy with DBA scheme for improved performance in terms of different QoS parameters like New Call Blocking Probability (NCBP), Hand off Call Dropping Probability (HCDP) and Bandwidth Utilization (BU). A Continuous Time Markov Chain based mathematical model is also developed for the realistic analysis of those QoS parameters. The Joint CAC and DBA scheme (JCAC-DBA) in two-tier LTE BWA Het-Nets significantly improves NCBP, HCDP, BU and overall capacity of the network under different combinations of macro/small cells for heterogeneous multimedia services.

The existing Internet provides best effort service. As such the quality of service (QoS) perceived by a user is inconsistent and unpredictable. In particular, the QoS for such applications is often poor when the links between communicating entities are congested or subject to sudden and unpredictable traffic surge. It is therefore desirable to introduce new service architecture in the Internet that guarantees QoS to continuous media application. The DiffServ architecture combined with multi protocol label switching (MPLS) have become a promising mechanism of achieving QoS with the scalability required by the Internet. MPLS achieves fast forwarding of packets through its connection-oriented framework. The MPLS edge router assigns packets with labels. Label switched routers in the MPLS core network direct the packets based on their labels. This paper addresses the resource allocation concerns at the DiffServ-enabled MPLS edge node. A DiffServ-MPLS dynamic link bandwidth allocation engine is described. The link bandwidth allocation engine is based on fuzzy logic and the maximum bandwidth allocation scheme. This work demonstrates that the fuzzy logic scheduler can be used in a hierarchical manner, where it first allocates link bandwidth based on three main traffic classes, i.e. premium, assured and best effort and then divides and allocates the bandwidth in the assured class further, i.e. gold, silver and bronze.

The consolidation of multiple servers and their workloads aims to minimize the number of servers needed thereby enabling the efficient use of server and power resources. At the same time, applications participating in consolidation scenarios often have specific quality of service requirements that need to be supported. To evaluate which workloads can be consolidated to which servers we employ a trace-based approach that determines a near optimal workload placement that provides specific qualities of service. However, the chosen workload placement is based on past demands that may not perfectly predict future demands. To further improve efficiency and application quality of service we apply the trace-based technique repeatedly, as a workload placement controller. We integrate the workload placement controller with a reactive controller that observes current behavior to i) migrate workloads off of overloaded servers and ii) free and shut down lightly-loaded servers. To evaluate the effectiveness of the approach, we developed a new host load emulation environment that simulates different management policies in a time effective manner. A case study involving three months of data for 138 SAP applications compares our integrated controller approach with the use of each controller separately. The study considers trade-offs between i) required capacity and power usage, ii) resource access quality of service for CPU and memory resources, and iii) the number of migrations. We consider two typical enterprise environments: blade and server based resource pool infrastructures. The results show that the integrated controller approach outperforms the use of either controller separately for the enterprise application workloads in our study. We show the influence of the blade and server pool infrastructures on the effectiveness of the management policies.

Running multiple virtual machines over a real physical machine is a promising way to provide agility in current data centers. Virtual machines belong to one application are striped over multiple nodes, and the generated traffic often shares the substrate network with other traffic of other applications. In such conditions, clients can experience severely degraded performance, such as TCP throughput collapse and network congestion due to competing network traffic. The basic cause of this problem is that network traffic from multiple sources which shares the same network link can cause transient overloads in the link. In this paper, we make the case that network virtualization opens up a new set of opportunities to solve such congestion performance problem. We present an architecture which compartmentalize virtual machines of same application into same virtual networks by network slicing, and divides the role of the traditional ISPs into two: infrastructure providers and service providers to achieve more commercial agility needed by cloud computing in particular. We also present a dynamic bandwidth allocation mechanism, which can prevent congestion and maximize utilization of substrate networks. Experimental result shows that the network slicing mechanism and bandwidth allocation algorithm can prevent network congestion significantly.

The IEEE 802.11n supports high data rate transmissions due its physical layer Multiple Input ‎Multiple Output (MIMO) advanced antenna system and MAC layer enhancement features (frame ‎aggregation and block acknowledgement). As a result this standard is very suitable for multimedia ‎services through its Enhanced Distributed Channel Access (EDCA). This paper focuses on ‎evaluating the Quality of Service (QoS) application on the performance of the IEEE 802.11n ‎random topology WLAN. Three different number of nodes (3, 9 and 18) random topology with one ‎access point are modeled and simulated by using the Riverbed OPNET 17.5 Modular to ‎investigate the Wireless Local Area Network (WLAN) performance for different spatial streams. ‎The result clarified the impact of QoS application and showed that its effect is best at the 18 node ‎number topology. For a 4x4 MIMO, when QoS is applied and with respect to the no QoS ‎application case, simulation results show a maximum improvement of 86.4%, 33.9%, 52.2% and ‎‎68.9% for throughput, delay, data drop and retransmission attempts, respectively. ‎

Limited memory bandwidth is considered as the major bottleneck in multimedia cloud computing for more and more virtual machines (VMs) of multimedia processing requiring high memory bandwidth simultaneously. Moreover, contending memory bandwidth among parallel running VMs leads to poor quality of service (QoS) of the multimedia applications, missing the deadlines of these soft real-time multimedia applications. In this paper, we present an adaptive framework, Service Maximization Optimization (SMO), which is designed to improve the QoS of the soft real-time multimedia applications in multimedia cloud computing. The framework consists of an automatic detection mechanism and an adaptive memory bandwidth control mechanism. With the automatic detection mechanism, the critical section to the multimedia application performance in the VMs is detected. Then, our adaptive memory bandwidth control mechanism adjusts the memory access rates of all the parallel running VMs to protect the QoS of the soft real-time multimedia applications. From the case studies with real-world multimedia applications, our SMO significantly improves the QoS of the soft real-time multimedia applications with a negligible penalty on system throughput.

A fuzzy logic-based method for assessing and improving quality of service (QoS) in wireless networks has been developed. A suitable wireless network was simulated to transmit audio and video applications. The QoS for each application was assessed by developing a fuzzy logic system. The output of the fuzzy logic was used to adjust the minimum contention window (CWmin) value of the IEEE 802.11 medium access control (MAC) protocol. By using the devised method, the average QoS for both audio and video applications was significantly improved compared with the conventional IEEE 802.11 DCF 802.11 protocol.

WDM based passive optical network (PON) upgrades current TDM based PON at the architecture, protocol and dynamic bandwidth allocation algorithms to provide higher bandwidth in the access networks. Various Dynamic Wavelength and Bandwidth Allocation algorithms for WDM-PON have been studied. These DWBA algorithms exploit both inter-channel and intra-channel statistical multiplexing in order to achieve better performance, especially when the load on various channels is not symmetric. However, these algorithms let all ONUs share all wavelengths equally, and decouple bandwidth allocation from the wavelength assignment, which may cause bandwidth fragmentation across different wavelengths, and these algorithms further strictly limit the ONUs only to use one wavelength per allocation cycle, hence, leading to the underutilized network performance. To overcome the above limitation, we propose an enhanced dynamic wavelength and bandwidth allocation (EDBA) algorithm, which integrates wavelength assignment with bandwidth allocation process. We use extensive simulation to compare the performance of EDBA to another DWBA algorithm in³.