Search

One of TCP's key tasks is to react and avoid network congestion episodes which normally arise in packet switched networks. A wide literature is available concerning the behaviour of congestion control algorithms in many different scenarios and several congestion control algorithms have been proposed in order to improve performances in specific scenarios. In this paper we focus on the UMTS wireless scenario and we report a campaign of measurements that involved around 3000 flows and more than 40 hours of measurements using three different TCP stacks: TCP NewReno, which is the congestion control algorithm standardized by IETF, TCP BIC which is the default congestion control algorithm adopted by the Linux operating system, and TCP Westwood+ also available in the Linux kernel. The experimental evaluation has been carried out by accessing the public Internet using an UMTS card. Measurements of goodputs, RTTs over time, packet loss ratios, number of timeouts and Jain Fairness Indices are reported through cumulative distribution functions. Moreover, the efficiency of each TCP version in transferring files has been evaluated by varying the file size in the range from 50 KB up to 500 KB. The cumulative distribution functions reported in the paper show interesting results: 1) a single downlink flow is far from saturating the channel bandwidth; 2) considered TCP stacks provide similar results; 3) 90th (50th) percentile of the goodput of a single downlink flow is less or equal then 230 kbps (120 kbps) compared to a nominal 384 kbps UMTS downlink channel. [ABSTRACT FROM AUTHOR]

In this paper, we first analyze the medium access delay of a packet in a terminal in the saturated IEEE 802.11 network. In our analysis, we use the renewal theory to analyze the detailed packet transmission processes of terminals in the network such as the backoff counter freezing. Using our detailed analysis of the packet transmission processes of terminals, we analyze the packet transmission process of a tagged terminal and the background traffic for the tagged terminal which is generated by non-tagged terminals, and derive the Laplace transform of the medium access delay of a packet under the saturated condition. Next, based on the analysis of the medium access delay under the saturated condition, we propose a mathematical model to analyze the packet overflow probability of an unsaturated terminal. We also provide numerical and simulation results to validate our analysis and investigate the characteristics of the system performance. IEEE 802.11 WLAN, Distributed Coordination Function, Medium Access Delay, Performance Evaluation, Packet Overflow Probability [ABSTRACT FROM AUTHOR]

In this paper we consider a problem of implementing a hybrid routing protocol for wireless sensor networks, which natively supports data-centric, geographic-based and address-centric communication paradigms. We demonstrate the feasibility of such protocol by presenting tinyLUNAR, an adapted to the specifics of sensor networks reactive routing scheme originally developed for mobile wireless ad hoc networks. In addition to the support for several communications paradigms tinyLUNAR implements highly efficient multihop forwarding using only 1 B field that can be directly encoded in the standard IEEE 802.15.4 MAC header. [ABSTRACT FROM AUTHOR]

Network-based Localized Mobility Management (NetLMM) is an outstanding candidate solution for the mobility management controlled by the network. In NetLMM, mobile nodes (MNs) can be provided mobility services without any installation of mobility-support stack. However, there is a restriction that the MN is able to have the mobility only within a single localized mobility domain (LMD). In this paper, we propose a novel Inter-LMD handoff mechanism in order to eliminate the shortcoming of the current NetLMM protocol. The proposed Inter-LMD handoff mechanism enables that the MN hands off across LMDs, even if the MN does not have a functionality of Mobile IPv6 (MIPv6). According to the performance evaluation, the proposed Inter-LMD handoff mechanism has approximately 5.8% more overhead than the current Inter-LMD handoff of MIPv6-capable devices, while the current NetLMM protocol does not support the handoff of MIPv6-incapable devices. [ABSTRACT FROM AUTHOR]

Existing wireless networks have little in common, as they are designed around vendor-specific devices that use specific radio access technologies to provide particular functionality. Next generation networks seek to integrate wired and wireless networks in order to provide seamless services to the end user. Seamless Mobility is an experiential architecture, predicated on providing mechanisms that enable a user to accomplish his or her tasks without regard to technology, type of media, or device. This paper examines how autonomic mechanisms can satisfy some of the challenges in realizing seamless mobility solutions. [ABSTRACT FROM AUTHOR]

In location tracking, there is a trade-off between data accuracy of mobile targets and energy efficiency of sensor nodes. If the number of nodes is increased to track a mobile target, the level of data accuracy increases, but the energy consumption of nodes increases. In this paper, we propose a new location tracking scheme that considers these two factors. The proposed scheme is designed to track mobile targets in a cluster-based sensor network. In order to increase the energy efficiency of sensor nodes, a portion of nodes that detect the mobile target is selected to track the target using the backoff procedure. In addition, we consider data accuracy as controlling the number of nodes by varying the transmission range of the nodes. We perform a simulation to evaluate the performance of the proposed scheme over sensor networks. We provide simulation results comparing the proposed scheme with the general approach. The simulation results show that the proposed scheme has the excellent performance over a broad range of parameters. [ABSTRACT FROM AUTHOR]

A potential solution for building ad-hoc networks is described. It is based on the Technoconcepts' TSR chipset. This chipset provides direct conversion of RF signals to baseband. Such RF/DTM chips convert the received signals into digital form immediately after the antenna, making it possible to provide all required signal processing in digital form, thus allowing adaptive frequency bands free of interference. This flexibility provides the most favorable conditions for quality communications. The offered solution has its own set of challenges. The paper describes the major challenges, and the potential ways of addressing them. An example of possible ad-hoc network architectures is presented that is based on the RF/DTM chips. [ABSTRACT FROM AUTHOR]

The functioning of an ad hoc network is based on the supportive contributions of all of its members. Nodes behave as routers and take part in route discovery and maintenance. In this paper, a forwarding protocol is presented that stimulates node cooperation to improve the throughput of the network. The incentive mechanism is provided through a micropayment protocol that deals with the cooperation range of the users. Most cooperative nodes intrinsically benefit of the best routes and availability and they take preference in front of selfish ones. [ABSTRACT FROM AUTHOR]

In telecommunications networks, usually an aggregation of information units (a batch) is transmitted instead of individual information units. In order to obtain performance measures for such networks, we analyze a discrete-time queueing model with a batch server operating under the minimum batch size (MBS) service policy. Specifically, we calculate the steady-state probability generating function (PGF) of the system contents at the beginning of an arbitrary slot. This PGF enables us to derive some important performance measures. Furthermore, we investigate, through some numerical examples, the influence of some parameters on the optimal choice of the MBS. In this paper, we focus on the influence of the load and the distribution of the service times. [ABSTRACT FROM AUTHOR]

Mobile WiMAX is a promising wireless technology approaching market deployment. Much discussion concentrate on whether mobile WiMAX will reach a tipping point and become 4G or not. As a pre-mobile WiMAX system is being delivered, we decided to set up a real life field trial and perform the most important measurements over the system setup. The system was delivered with 4th order diversity. In this paper we analyze physical system performance based on field trial measurements, especially at locations with non line of sight conditions in urban areas. We investigate the gain with 2nd and 4th order base station diversity and derive analytical expressions. The system path loss is plotted and found to approach the Cost-231 Hata model for urban areas. Throughput is also measured and analyzed. Sub-channelization in the uplink points out to be an important feature for enhanced coverage. [ABSTRACT FROM AUTHOR]

The performance of a TCP protocol on MANETs has been studied in a numerous researches. It has been shown that performance of TCP on MANET is poor and that it is caused by two groups of reasons: one inherited from wireless networks and one caused by nodes mobility. One reason of TCP degradation is inability to distinguish between packet losses due to congestion from those caused by nodes mobility and as consequence broken routes. This paper presents the Cluster-Label-based Routing protocol that is an attempt to compensate source of TCP problems on MANETs - multi-hop mobile environment. By utilizing Cluster-Label-based mechanism for Backbone the CLR is able to concentrate on detection and compensation of movement of a destination node. The proposed protocol provides better goodput and delay performance than standardized protocols especially in cases of large network size and/or high mobility rate. [ABSTRACT FROM AUTHOR]

Real-time traffic aggregates are often characterized by time-varying nature. However, resources for this kind of traffic are usually allocated assuming busy hour stationary traffic characteristics. This assumption may lead to inefficient use of network resources when static resource reservation is used. In this paper we propose the algorithm for on-line estimation of the traffic state in terms of piecewise weakly stationary stochastic process. As a basic tool of the algorithm we use change-point statistical test allowing us to dynamically and automatically determine whether the traffic pattern changes and, if so, estimate new parameters of the traffic pattern. Assuming that a network may assign the required resources on-demand on a per-node basis, the proposed procedure helps to decide which amount of resources should be assigned to handle the traffic with given performance metrics. The proposed algorithm is well-suited for non-stationary behavior of the aggregated traffic where statistical parameters change in time. The computational complexity of the algorithm is low and it can be implemented on a traffic class basis making the proposal suitable for backbone routers. [ABSTRACT FROM AUTHOR]

This paper provides recent empirical traffic data and observations of telephony traffic patterns in mobile and IP telephony. These are compared with old telephony patterns from Public Switched Telephone Networks (PSTN) to investigate potential evolution and impact on traffic characterisations due to technology changes from fixed to mobile phones, changes in quality from fixed phone to mobile and IP telephone, changes in tariffs from usage based to flat-rate subscriptions, and appearance of alternative message based communication means. The results show different daily and weekly traffic profiles compared to PSTN telephony. In particular, the profile of international calls is significantly changed. Furthermore, the average call holding times show significant variations over the day in flat-rate subscriptions. Finally, the results indicate that the Short Message Service (SMS) seems to serve as a supplement to phone calls, in particular in the evenings, which might change call holding time distribution and traffic intensities. [ABSTRACT FROM AUTHOR]

In this paper we analyze measurements from the Finnish University Network (Funet) and study the effect of spatial aggregation on the origin- destination flows. The traffic is divided into OD pairs based on IP addresses, using different prefix lengths to obtain data sets with various aggregation levels. We find that typically the diurnal pattern of the total traffic is followed more closely by the OD pairs as their volume increases, but there are many exceptions. Gaussian assumption holds well for all OD pairs when the aggregation level is high enough, and we find an approximate threshold for OD pair traffic volume after which they tend to be Gaussian. Also the functional mean-variance relation holds better when the aggregation level is higher. [ABSTRACT FROM AUTHOR]

In this paper, we analyze backoff protocols, such as Ethernet. We examine a general backoff function (GBF) rather than just the binary exponential backoff (BEB) used by Ethernet. Under some mild assumptions we find stability and optimality conditions for a wide class of backoff protocols with GBF. In particular, it is proved that the maximal throughput rate over the class of backoff protocols with N stations is $\left(1-\frac1N\right)^{\frac1{N-1}}$ and the optimal average service time for any station is $E S = N/\left(1-\frac1N\right)^{\frac1{N-1}}$ or about Ne for large N. The reasons of the instability of the BEB protocol (for a big enough input rate) is explained. [ABSTRACT FROM AUTHOR]

In this paper we embrace an engineering approach to service delivery over the Internet, by presenting an actual implementation of a conferencing framework compliant with the IP Multimedia Core Network Subsystem (IMS) specification. The architecture we describe has been conceived at the outset by taking into account ongoing standardization efforts inside the various active international bodies. At its current state, it is capable to provide video conferencing facilities with session management capabilities and floor control. The system presented is intended to serve as a running experimental testbed useful for protocol testing, as well as field trials and experimentations. It will be first described from a high level design perspective and subsequently analyzed in further detail by highlighting the most notable implementation choices. A mapping between the actual system components and the corresponding IMS logical functions will be provided and a discussion concerning those parts of the system which somehow depart from the IMS paradigm will be conducted. This on one hand will help the reader figure out potential discrepancies between our solution and the IMS model; on the other hand will open space for discussion around some important open issues on which the international research community still has to attain a rough consensus. [ABSTRACT FROM AUTHOR]

Ethernet protocol originally designed local area networks became very popular and in practice the only protocol used in local and metropolitan networks. Currently both IETF and IEEE are working on some improvements of this protocol to make it more attractive for usage in WAN networks. These modifications may add some additional fields into ethernet header so that the effective maximum transportable data unit will be decreased. From this point follows the problem how to inform upper layers about maximum data unit which ethernet layer can transport. This problem is not addressed in prepared IETF and IEEE standards. This paper tries to point out to this problem and propose some possible solutions. [ABSTRACT FROM AUTHOR]

It is well-known that the transmission control protocol (TCP) does not perform well in wireless and satellite environments. We investigate the use of cross-layer design involving the transport and medium access control (MAC) layers in the context of a geostationary bandwidth-on-demand satellite network to simultaneously enhance TCP performance and to improve bandwidth utilization. In this paper, we focus on the slow-start phase of the connection. In essence, we create a bandwidth pipe between the two layers so that through cross-layer interactions, the TCP connections are aware of the satellite resources available to them, thus adjusting their congestion window accordingly. Our proposal includes minimal changes to the original protocol, allowing easier integration and inter-working with existing infrastructure. Our evaluation results show a shorter slow-start duration with better bandwidth utilization. Although the performance gain is higher in a lossy satellite link, we also found that it is dependent on the network load. [ABSTRACT FROM AUTHOR]

Multirate wireless networks in general share a common problem for the transmission of VoIP traffic, since the rate changes of some of the flows affect the transmission of all others, which causes an unacceptable voice quality degradation. In this work, an admission control algorithm is combined with a codec selection block to mitigate this negative effect. This centralized admission control is able to block or drop calls in order to maintain the system stability despite rate changes. Moreover, the integrated codec selection block is able to select the most adequate VoIP codec for each incoming or already active call based on the channel rate used and according to a number of optimization policies. Several such policies are designed and evaluated in this paper. Results show that this combined adaptive solution provides a beneficial trade-off among the performances of the different codecs in terms of MOS, blocking and dropping probability and cell resource usage. Furthermore, a number of interesting singularities deriving from the multirate nature of the network are identified. [ABSTRACT FROM AUTHOR]

A goal of modern broadband networks is their ability to provide stringent QoS guarantees to different classes of users. This feature is often related to events with a small probability of occurring, but with severe consequences when they occur. In this paper we focus on the overflow probability estimation and analyze the performance of Bridge Monte-Carlo (BMC), an alternative to Importance Sampling (IS), for the Monte-Carlo estimation of rare events with Gaussian processes. After a short description of BMC estimator, we prove that the proposed approach has clear advantages over the widespread single-twist IS in terms of variance reduction. Finally, to better highlight the theoretical results, we present some simulation outcomes for a single server queue fed by fraction Brownian motion, the canonical model in the framework of long range dependent traffic. [ABSTRACT FROM AUTHOR]

With the increase of wireless network and demand for the variety of services, the handoff resource reservation for the Quality of Service(QoS) will be significant issue in future wireless networks. But on the other hand, the efficiency of resource usage also needs to be considered for preventing waste of network resources due to the reservation. Therefore, this paper suggests an efficient resource reservation scheme to support QoS provision as well as the efficient resource utilization simultaneously. In the proposed scheme, handoff probability estimation with the filtering algorithm is used to calculate the optimal amount of resources to be reserved in the neighbor cells. So, the mobile units with the proposed scheme can predict the amount of resources required in the future and reserve resource effectively. The performance simulation shows that the proposed scheme is advantageous with the balance of QoS provision and resource utilization in the wireless network. [ABSTRACT FROM AUTHOR]

Orthogonal variable spreading factor (OVSF) codes are widely used to provide variable data rates for supporting different bandwidth requirements in wideband code division multiple access (WCDMA) systems. Many works in the literature have intensively investigated to find an optimal dynamic code assignment scheme for OVSF codes. Unlike earlier studies, which assign OVSF codes using conventional (CCA) or dynamic (DCA) code allocation schemes, in this paper, stochastic optimization methods which are genetic algorithm (GA) and simulated annealing (SA) were applied which population is adaptively constructed according to existing traffic density in the OVSF code-tree. Simulation results show that the GA and SA provide reduced code blocking probability and improved spectral efficiency when compared to the CCA and DCA schemes. It is also seen that, computational complexity of GA and SA are also more than CCA and DCA. [ABSTRACT FROM AUTHOR]

The IEEE 802.16 technology defines the ARQ mechanism that enables a connection to resend data at the MAC level if an error is detected. In this paper, we analyze the key features and parameters of the ARQ mechanism. In particular, we consider a choice for the ARQ feedback type, a scheduling of the ARQ feedbacks and retransmissions, the ARQ block rearrangement, ARQ transmission window and ARQ block size. We run a number of simulation scenarios to study these parameters and how they impact a performance of application protocols. The simulation results reveal that the ARQ mechanism plays an important role in transmitting data over wireless channels in the IEEE 802.16 networks. [ABSTRACT FROM AUTHOR]

Virtual Private Networks (VPNs) are replacing expensive leased lines since they use the public Internet as the communication channel. However, Internet by itself does not provide guarantees of security and QoS to send voice and video packets. In this paper we present a generic security and QoS model named GESEQ which is based on the DiffServ model that shows design considerations when delay-sensitive packets need to be protected by IPSec tunnels and also need to be treated preferentially to overcome the increase of packet latency, jitter and packet loss under network traffic congestion. We made and present a particular test scenario and its quantitative analysis to prove that GESEQ works efficiently when trying to send voice and video packages with security and QoS. [ABSTRACT FROM AUTHOR]

We present a comprehensive analysis of the packet loss process in a finite-buffer queue fed by the Markov-modulated Poisson process. In particular, solutions for the number of losses in (0,t], the stationary number of losses and the loss ratio are presented in closed forms. Theoretical results are illustrated via numerical examples based on an IP traffic trace file. [ABSTRACT FROM AUTHOR]

The current architecture of the Internet where anyone can send anything to anybody presents many problems. The recipient of the connection might be using a mobile access network and thus unwanted incoming connections could produce a high cost to the recipient. In addition, denial of service attacks are easy to launch. As a solution to this problem, we propose the Recipient Controlled Session Management Protocol where all incoming connections are denied by the default and the recipient of the connection can choose using certificates what incoming connections are allowed. The recipient can also revoke rights for making an incoming connection at any time. [ABSTRACT FROM AUTHOR]

There is ongoing work on the IETF aimed to provide support for different flavors of multihoming configurations, such as SHIM6 for multihomed sites, multiple CoAs support in MIP for multihomed mobile nodes and HIP for multihomed nodes and sites. A critical aspect for all the resulting multihoming protocols is to detect failures and gain information related with the paths available between two hosts. The Failure Detection and Locator Path Exploration Protocol (in short REAchability Protocol, REAP) being defined in the SHIM6 WG of the IETF is a good candidate to be included as a reachability detection component on protocols requiring this functionality. Performance study is performed by combining analytical estimations and simulations to evaluate its behavior and tune its main parameters. [ABSTRACT FROM AUTHOR]

Dynamic Source Routing (DSR) is an efficient on-demand routing protocol for ad hoc networks, in which only needed routes are found and maintained. The route discovery/setup phase becomes the dominant factor for applications with short-lived small transfer traffic (one single packet or a short stream of packets per transaction) between the source and the destination: resource discovery, text-messaging, object storage/retrieval, queries and short transactions. Route caching is helpful to avoid the need for discovering a route or to shorten route discovery delay before each data packet is sent. The goal of this work is to develop a caching strategy that permits nodes to update their cache quickly to minimize end-to-end delay for short-lived traffic. The proposed approach consists of an Active Packet that travels through the nodes of the network twice. During the first travel, it visits the nodes collecting fresh network topology information. When the first visit is finished, another one is started to validate and update the caches of the nodes with this newly obtained information. This mechanism removes invalid cache links and caches valid links based on the collected topology information. The correct information in caches allows to speed up the Route Discovery and even to avoid it. [ABSTRACT FROM AUTHOR]

IEEE 802.16 is yet a very recent technology and released hardware does frequently only support standards partially. The same applies to public available simulation tools, in particular for NS-2. As the latter is the de-facto standard in science and as we use it for our research in the context of the WEIRD project, we evaluate the of IEEE 802.16 support for NS-2. We present several general but also specific issues, which are important in order to carry out reliable research based on these tools. In particular, we show in much detail where modules deviate significantly and even fail totally. [ABSTRACT FROM AUTHOR]

A mobile ad hoc network (MANET) station acts both as a source packet generator and transit packet forwarder. With selfish stations and the absence of administrative cooperation enforcement, the lack of forwarding incentives has long been recognized as a serious design problem in MANETs. Reputation systems discourage selfishness by having past cooperation increase the present source packet throughput. We describe a simple watchdog-controlled first-hand reputation system and point to a form of selfishness not addressed by existing research, arising from packet anonymity. If the watchdog at a station cannot tell a nearby station's source packets from transit packets, that station is tempted to admit more source packet traffic than a fair local admittance control (LAC) scheme permits. We analyze a related noncooperative LACgame and characterize three types of its Nash equilibria. Next we propose a simple packet forwarding protocol by the name Decline and Force (D&F) and using an approximate performance model show that, when properly configured, D&F leads to a fair and efficient game outcome. [ABSTRACT FROM AUTHOR]

Derivatives of blocking probabilities of multi-service loss networks are important for traffic engineering. An explicit formula for the derivatives of blocking probabilities with respect to offered traffics is obtained expressed by stationary probabilities of global state probabilities. The approach is based on the convolution algorithm. It allows us to find expressions for the derivatives in a much more easy way than known so far. It is briefly shown how derivatives can be applied for approximate evaluation of performance measures and for studying the error of performance measures estimation caused by small changes of offered traffic. The results can also be applied for network optimization. [ABSTRACT FROM AUTHOR]

In cellular networks, repeated attempts occur as result of user behavior but also as automatic retries of blocked requests. Both phenomena play an important role in the system performance and therefore should not be ignored in its analysis. On the other hand, an exact Markovian model analysis of such systems has proven to be infeasible and resorting to approximate techniques is mandatory. We propose an approximate methodology which substantially improves the accuracy of existing methods while keeping computation time in a reasonable value. A numerical evaluation of the model is carried out to investigate the impact on performance of the parameters related to the retry phenomena. As a result, some useful guidelines for setting up the automatic retries are provided. Finally, we also show how our model can be used to obtain a tight performance approximation in the case where reattempts have a deterministic nature. [ABSTRACT FROM AUTHOR]

In support of the on-going research and development activity in the design and performance assessment of radio access network integration schemes, we present novel resource sharing models for the efficient simulation of multi-access networks involving gsm/edge, umts/hsdpa and 802.11a-based wlan systems. The applicability of the proposed models in determining call and system level performance measures is demonstrated by means of a limited set of illustrative numerical experiments revealing the significant performance gains when integrating distinct access networks with a rather simple radio access selection scheme. [ABSTRACT FROM AUTHOR]

Optical packet switching (OPS) is a promising technology for future generation networks solutions. One of the great challenges to be addressed is differentiated quality of service (QoS) and a major concern in providing QoS is packet loss. In case of differentiated services, packet losses should be significantly less likely for high priority classes than for low priority classes. However, as packet losses are very unlikely they become rare events which poses serious challenges to conventional analysis methodologies. We present an importance sampling scheme for fast simulation of packet loss rates in this setting. The change of measure adapts according to ant colony optimization, a metaheuristic inspired by the foraging behavior of ants. Thereby, our simulation does not require intimate a priori knowledge of the system and overcomes a general drawback of importance sampling. Within very moderate simulation time, accurate results are provided for an OPS model with varying parameter settings. [ABSTRACT FROM AUTHOR]

We propose and analyse a discrete-time queueing model for the evaluation of the IEEE 802.16e sleep mode operation in wireless access networks. This mechanism reduces the energy consumption of a mobile station (MS) by allowing it to turn off its radio interface (sleep mode) when there is no traffic present at its serving base station (BS). After a sleep period expires, the MS briefly checks the BS for data packets and switches off for the duration of another sleep period if none are available. Specifically for IEEE 802.16e, each additional sleep period doubles in length, up to a certain maximum. Clearly, the sleep mode mechanism can extend the battery life of the MS considerably, but also increases the delay at the BS buffer. For the analysis, we use a discrete-time queueing model with general service times and multiple server vacations. The vacations represent the sleep periods and have a length depending on the number of preceding vacations. Unlike previous studies, we take the traffic correlation into account by assuming a D-BMAP arrival process. The distribution of the number of packets in the queue is obtained at various sets of time epochs, as well as the mean packet delay and the mean number of consecutive vacations. We apply these results to the IEEE 802.16e sleep mode mechanism with downlink traffic. By means of some examples, we show the influence of both the configuration parameters and the traffic correlation on the delay and the energy consumption. [ABSTRACT FROM AUTHOR]

The development of e-Health services in rural environments, where broadband networks are usually not accessible, requires a specific analysis of available resources to improve Quality of Service (QoS) management. This work quantifies the maximum number of simultaneous users that fulfill the specific QoS levels in common e-Health services, including both store-and-forward and real-time telemedicine applications. The analysis also proposes variations in the modelling of traffic distributions regarding the number of multiplexed users. The results obtained in this study permit an accurate users dimensioning, which is necessary to optimize the performance and to guarantee the QoS requirements in this kind of services where network resources are limited. [ABSTRACT FROM AUTHOR]