Current literature on input buffer management reveals that, in representative ATM networks under highly bursty traffic conditions, the fuzzy thresholding approach yields lower cell loss rate at the cost of lower throughput. Also, under less bursty traffic, the traditional fixed thresholding approach achieves higher throughput at the expense of higher cell loss rate. The integration of these two properties into practice is termed adaptive dynamic buffer management (ADBM) approach for input buffers and its assessment is the objective of this paper. The argument is that, given that the traffic conditions are constantly changing, to achieve efficiency during actual operation, the network control must dynamically switch, at every ATM switch, under the call processor's control, between the two input buffer management techniques, dictated by the nature of the traffic at the inputs of the corresponding switch. The need to involve the call processor marks the first effort in the literature to dynamically configure input buffer management architectures at the switch fabric level under higher level call processor control. It stems from the fact that the switch fabric operates very fast and cannot engage in complex decision making without incurring stiff penalty. To achieve this goal, the network control needs knowledge of the burstiness of the traffic at the inputs of every ATM switch. The difficulties with this need are two-fold. First, it is not always easy to obtain the traffic model and model parameters for a specific user's call. Second, even where the traffic model and the model parameters are known for a specific user's call, this knowledge is valid only at the source switch where the user interfaces with the network. At all other switches in the network, the cells of the traffic in question interact asynchronously with the cells from other traffic sources and are subject to statistical multiplexing. Thus, to obtain the exact nature of the composite traffic at the inputs of any ATM switch, is a challenge. Conceivably, one may determine the burstiness by counting the number of cells incurred at the inputs of an ATM switch over a defined time interval. The challenge posed by this proposition lies in the very definition of burstiness in that the time interval must approach, in the limit, zero or the resolution of time in the network. To address this challenge, first, a 15-node representative ATM network is modeled in an asynchronous, distributed simulator and, second, simulated on a network of workstations under realistic traffic stimuli. Third, burstiness indices are measured for the synthetic, stochastic traffic at the inputs of every ATM switch as a function of the progress of simulation for different choices of time interval values, ranging from 20,000 timesteps down to 1,000 timesteps. A timestep equals 2.73 µs. Results reveal that consistent burstiness indices are obtained for interval choices between 1,000 and 5,000 timesteps and that a burstiness index of 25, measured at 3,000 timestep interval, constitutes a reasonable and practical threshold value that distinguishes highly bursty traffic that warrants the use of the fuzzy thresholding approach from less bursty traffic that can benefit from the fixed thresholding scheme. A comparative performance analysis of ADBM yields the following. For pure fixed and pure fuzzy thresholding schemes, the throughputs are at 73.88% and 71.53% while the cell drop rates are at 4.31% and 2.44%,respectively. For the ADBM approach, where the input buffer management alternates at each individual ATM switch between the fixed and fuzzy schemes, governed by measured burstiness index threshold of 25 for a 3,000 timestep interval, the throughput is 74.77%, which is higher than even the pure fixed scheme while the cell drop rate is 2.21% that is lower than that of the pure fuzzy scheme. In essence, ADBM successfully integrates the best characteristics of the fuzzy and fixed thresholding schemes.

A principal attraction of ATM networks, in both wired and wireless realizations, is that the key quality of service (QoS) parameters of every call, including end-to-end delay, jitter, and loss are guaranteed by the network when appropriate cell-level traffic controls are imposed at the user network interface (UNI) on a per call basis, utilizing the peak cell rate (PCR) and the sustainable cell rate (SCR) values for the multimedia--voice, video, and data, traffic sources. There are three practical difficulties with these guarantees. First, while PCR and SCR values are, in general, difficult to obtain for traffic sources, the typical user-provided parameter is a combination of the PCR, SCR, and the maximum burstiness over the entire duration of the traffic. Second, the difficulty in accurately defining PCR arises from the requirement that the smallest time interval must be specified over which the PCR is computed which, in the limit, will approach zero or the network's resolution of time. Third, the literature does not contain any reference to a scientific principle underlying these guarantees. Under these circumstances, the issue of providing QoS guarantees in the real world, through traffic controls applied on a per call basis, is rendered uncertain. This paper adopts a radically different, high level approach to the issue of QoS guarantees. It aims at uncovering through systematic experimentation a relationship, if any exists, between the key high level user traffic characteristics and the resulting QoS measures in a realistic operational environment. It may be observed that while each user is solely interested in the QoS of his/her own traffic, the network provider cares for two factors: (1) Maximize the link utilization in the network since links constitute a significant investment, and (2) ensure the QoS guarantees for every user traffic, thereby maintaining customer satisfaction. Based on the observations, this paper proposes a two-phase strategy. Under the first phase, the average "link utilization" computed over all the links in a network is maintained within a range, specified by the underlying network provider, through high level call admission control, i.e. by limiting the volume of the incident traffic on the network, at any time. The second phase is based on the hypothesis that the number of traffic sources, their nature--audio, video, or data, and the bandwidth distribution of the source traffic, admitted subject to a specific chosen value of "link utilization" in the network, will exert a unique influence on the cumulative delay distribution at the buffers of the representative nodes and, hence, on the QoS guarantees of each call. The underlying thinking is as follows. The cumulative buffer delay distribution, at any given node and at any time instant, will clearly reflect the cumulative effect of the traffic distributions of the multiple connections that are currently active on the input links. Any bounds imposed on the cumulative buffer delay distribution at the nodes of the network will also dominate the QoS bounds of each of the constituent user traffic. Thus, for each individual traffic source, the buffer delay distributions at the nodes of the network, obtained for different traffic distributions, may serve as its QoS measure. If the hypothesis is proven true, in essence, the number of traffic sources and their bandwidth distribution will serve asa practically realizable high level traffic control in providing realistic QoS guarantees for every call. To verify the correctness of the hypothesis, an experiment is designed that consists of a representative ATM network, traffic sources that are characterized through representative and realistic user-provided parameters, and a given set of input traffic volumes appropriate for a network provider approved link utilization measure. The key source traffic parameters include the number of sources that are incident on the network and the constituent links at any given time, the bandwidth requirement of the sources, and their nature. For each call, the constituent cells are generated stochastically, utilizing the typical user-provided parameter as an estimate of the bandwidth requirement. Extensive simulations reveal that, for a given link utilization level held uniform throughout the network, while the QoS metrics--end-to-end cell delay, jitter, and loss, are superior in the presence of many calls each with low bandwidth requirement, they are significantly worse when the network carries fewer calls of very high bandwidths. The findings demonstrate the feasibility of guaranteeing QoS for each and every call through high level traffic controls. As for practicality, call durations are relatively long, ranging from ms to even minutes, thereby enabling network management to exercise realistic controls over them, even in a geographically widely dispersed ATM network. In contrast, current traffic controls that act on ATM cells at the UNI face formidable challenge from high bandwidth traffic where cell lifetimes may be extremely short, in the range of µs. The findings also underscore two additional important contributions of this paper. First, the network provider may collect data on the high level user traffic characteristics, compute the corresponding average link utilization in the network, and measure the cumulative buffer delay distributions at the nodes, in an operational network. The provider may then determine, based on all relevant criteria, a range of input and system parameters over which the network may be permitted to operate, the intersection of all of which may yield a realistic network operating point (NOP). During subsequent operation of the network, the network provider may guide and maintain the network at a desired NOP by exercising control over the input and system parameters including link utilization, call admittance based on the requested bandwidth, etc. Second, the finding constitutes a vulnerability of ATM networks which a perpetrator may exploit to launch a performance attack.

A major challenge in the design of multimedia networks is to meet the quality of service (QoS) requirements of all admitted users. Regulation and scheduling are key factors for fulfilling such requirements. We propose a rate-based regulation-scheduling scheme in which the regulation function is modulated by both the tagged stream's characteristics and the state information fed-back from the scheduler. The rate-jitter and bandwidth share of each tagged connection are controlled appropriately by considering the system time and the queue length of the scheduler. Simulation results have shown that the proposed scheme works better than other rate-based disciplines.

This is the first paper to report the influence of fuzzy thresolding-based buffer management scheme on the end-to-end delay performance of cell switching networks including asynchronous transfer mode (ATM) networks. In this approach, the fraction of the selectively blocked cells, corresponding to the difference of cell loss due to buffer overflow, between the traditional fixed and fuzzy schemes, are re-routed to their final destinations. A 50-switch, representative, cell-switching network under fuzzy thresholding is first modeled, second, simulated on a testbed consisting of a network of 25+ Pentium workstations under Linux, configured as a loosely-coupled parallel processor, and third, its performance is studied under realistic input traffic conditions. A total of 10,000 user calls, generating between 1.0 and 1.5 million ATM cells, is stochastically distributed among the nodes. Performance analysis reveals that for different input traffic distributions ranging from light to moderate to heavy traffic, the re-routing approach successfully routes these blocked cells, although it causes the average end-to-end cell delay in the network to increase, compared to the fixed scheme, by a factor ranging from 1.65 for relatively light traffic to 6.7 for heavy traffic.

In this paper, new integrated schemes of scheduling real-time traffic and cell loss control in high speed ATM networks are proposed for multiple priorities based on variable queue length thresholds for scheduling and the Partial Buffer Sharing policy for cell loss control. In our schemes, the queues for buffering arriving cells can be constructed in two ways: one individual queue for each user connection, or one physical queue for all user connections. The proposed schemes are considered to provide guaranteed QoS for each connection and cell sequence integrity for virtual channel/path characteristics. Moreover, these new schemes are quite flexible and can realize different scheduling algorithms. This paper also provides the Stochastic Petri Net models of these integrated schemes and an approximate analysis technique, which significantly reduces the complexity of the model solution and can be applied to real ATM switch models. From the numerical results, we can see that our schemes outperform those well-known schemes such as the head-of-line (HOL) priority control and the queue length threshold (QLT) policy.

The major concern at a branch point in asynchronous transfer mode (ATM) networks for point-to-multipoint available bit rate (ABR) services is how to consolidate backward resource management (BRM) cells from each branch for a multicast connection. In this paper, we propose an efficient feedback consolidation algorithm based on an adaptive dynamic threshold (ADT) to eliminate consolidation noise and to reduce consolidation delay. The main idea of the ADT algorithm is that each branch point estimates the ABR traffic condition of the network through virtual queue estimation. Simulation results show that the proposed ADT algorithm can achieve a faster response in congestion status and a higher link utilization compared with the previous works.

The available bit rate (ABR) is an ATM service category that provides an economical support of connections having vague requirements. An ABR session may specify its peak cell rate (PCR) and minimum cell rate (MCR), and available bandwidth is allocated to competing sessions based on the max-min policy. In this paper, we investigate the ABR traffic control from a different point of view: Based on the decentralized bandwidth allocation model studied in [9], we prove that the max-min rate vector is the equilibrium of a certain system of noncooperative optimizations. This interpretation suggests a new framework for ABR traffic control that allows the max-min optimality to be achieved and maintained by end-systems, and not by network switches. Moreover, in the discussion, we consider the constrained version of max-min fairness and develop an efficient algorithm with theoretical justification to determine the optimal rate vector.

A model of interactive videoconference is proposed for investigating the interactivity of the videoconference. Through running a prototype videoconferencing system over ATM networks, we observed that the system stability would degrade abruptly if the interaction demand from conferees exceeds what the system control can support. By using the proposed model, we formulate the problem of achieving high interactivity and stability as maximizing interactivity by tuning system parameters subject to some stability constraints. Solving the problem is non-trivial since it involves unpredictable network delays. We thus develop practical approaches that can choose and dynamically adjust, according to the network condition, the values of system parameters to meet the stability constraints and improve the interactivity. Finally, we validate our approaches and provide guidelines on choosing the parameter values by conducting experiments and simulations.

In order to make the ATM network fault-tolerant and the network service flexible, a method for the setting up of backup virtual paths (VP's for short) using multiagents is effective with respect to adaptability to change of network resource and user requirements, examples of which are failure of nodes and links and addition of VP's, respectively. In this method, under the assumption that candidates of backup VP's between different pairs of source and destination nodes are given, the optimum backup VP's are obtained by exchanging information among agents autonomously. First, this paper proposes measures for determining backup VP's between different pairs of source and destination nodes. Next, this paper presents simulation results to evaluate the adaptability of the method. The results show that the method efficiently obtains the optimum backup VP's even when the number of backup VP's increases and that different idle time at each destination node enables to shorten the total processing time while keeping complete detection of shared links.

It is always difficult to monitor stringent cell loss ratio (CLR), e.g. 10-9, in asynchronous transfer mode (ATM) networks, because its measurement period is too long for real-time measurement. In this paper, we propose new performance monitoring mechanisms for stringent CLR. We consider virtual ATM switches whose resources are much smaller than the real system and thus much higher CLRs will be obtained within a relatively short measurement period. By applying some regression methods in the CLRs obtained from the virtual system, we can estimate the actual CLR of the real system quite accurately and our performance monitoring mechanisms will be operated based on the estimation. Through the numerical examples, our mechanisms are not only more accurate than the traditional methods, but also have shorter measurement periods compared with direct measurement.

In this paper, we investigate the performance of Fast Reservation Protocols (FRP) for burst-level bandwidth allocation in ATM networks. FRP schemes can be classified into delayed transmission (DT) and immediate transmission (IT) methods according to reservation procedure. Moreover, according to the responsibility for negative acknowledgment (NAK) cell generations when burst blocking occurs, FRP schemes can be further classified into blocking node NAK (BNAK) and destination node NAK (DNAK) schemes. We analize the FRP schemes with different reservation and NAK methods for single node and multihop network models, respectively. We then discuss the dependence of performance for each FRP scheme on propagation delay, peak rate, and the number of hops.

This paper presents a real-time integrated traffic management (RITM) scheme that can effectively manage variable bit rate (VBR) and available bit rate (ABR) traffics having unpredictable characteristics in asynchronous transfer mode (ATM) networks. An unique feature of this scheme is that it has a special ATM cell control block, which makes it possible to monitor VBR and bursty traffics in real-time so that the delay incurred to measure cell arrival rate is minimized. In addition to its traffic monitor capability, the proposed scheme intends to dynamically reassign the leftover network resources to VBR/ABR connections without any deterioration in quality of service (QoS) of the existing connections. Particularly, we investigate into some functions of traffic management schemes that should be integrated to operate correctly in the emerging ATM networks. Also, we emphasize the merits of the RITM that has been developed to be a simple and efficient traffic management scheme to support the increasing data/Internet services and to get over difficulties in hardware complexities. The capability of managing the incoming ATM traffics in real-time helps determine an optimal acceptable number of user connections for a given network condition. We can use this value as a threshold to prevent the network from being congested and to find out a cost-effective buffer design method. This property makes the scheme extremely attractive as it supports most delay-sensitive and loss-sensitive applications at the same time without changing the existing ATM switching system architecture. The RITM scheme has been verified to reliably monitor incoming traffics and to efficiently manage network resources by computer simulations.

In this study, we propose a simple multipoint-to-point ABR mechanism that can be implemented easily in existing ATM networks. The proposed scheme can provide fair bandwidth allocation among the sources in multipoint-to-point connection.

The Virtual Path (VP) concept in ATM networks simplifies network structure, traffic control and resource management. For VP formulation, a VP can carry traffic of the same type (the separate scheme) or of different types (the unified scheme). For VP adjustment, a certain amount of bandwidth can be dynamically assigned (reserved) to VPs, where the amount (the bandwidth incremental/decremental size) is a predetermined system parameter. In this paper, we study Least Loaded Path-based dynamic routing schemes with various residual bandwidth definitions under different bandwidth allocation (VP formulation and adjustment) schemes. In particular, we evaluate the call blocking probability and VP set-up processing load with varying (bandwidth) incremental sizes. Also, We investigate numerically how the use of VP trades the blocking probability with the processing load. It is found that the unified scheme could outperform the separate scheme in certain incremental sizes. Moreover, we propose two ways to reduce the processing load without increasing the blocking probability. Using these methods, the separate scheme always outperforms the unified scheme.

This letter proposes a congestion control scheme for the ABR service of ATM networks which have non-responding connections. The control scheme is robust with respect to both the round trip delay and the loss of control information caused by non-responding connections. Thus, it is shown that the proposed control scheme guarantees the QoS of the network.

In this paper, we propose optimization approaches for the parameter determination of the PNNI complex node model. Two optimal objectives are discussed: Least Square Approximation and Maximum Deviation Minimization. For each objective, we propose two practical criteria for setting up bypasses: Maximum Difference Removal and Largest Deviation Removal. Generalized inverse of matrix and linear programming techniques are used to find the solutions. The numerical results show that the least square approximation with the largest deviation removal criteria has the best performance as the number of bypasses increases.

It is important to establish the technology to accommodate best effort TCP/IP traffic over wide area ATM networks. The UBR (Unspecified Bit Rate) service category is the most typical service category for the best effort traffic, especially in the LAN environment. On the other hand, the VBR (Variable Bit Rate) service category with SCD (Selective Cell Discard) option is considered as the service category which is appropriate for wide area networks due to its fairness and minimum guarantee of the cell transmission using not only PCR (Peak Cell Rate) but SCR (Sustainable Cell Rate) and MBS (Maximum Burst Size). However, there is no actual evaluation for such service. We have, therefore, performed the experimental studies on TCP/IP over VBR with SCD along with UBR and VBR without SCD by VC (Virtual Channel) level policing when each TCP connection is mapped to a different VC. Through these experiments, we measured the link utilization of the effective data and the fairness between each obtained TCP throughput during the congestion of the ATM switch. From the results of the link utilization, the value is over 95% under the various conditions. Therefore, even in the case of the cell losses due to SCD or buffer overflow in ATM switch congestion, average throughput is almost the same as the value which equals the trunk line speed divided by the number of the accommodated TCP connections. From the results of the fairness, VBR with SCD per VC is better than UBR and also obtains better TCP throughput than VBR without SCD. Furthermore, to confirm those characteristics more generally, we adopt the accommodated TCP connections not only with the same TCP send/receive socket buffer size but with different sizes. Finally, we discuss the effectiveness between VBR with SCD and the other service categories, such as UBR and ABR (Available Bit Rate) and GFR (Guaranteed Frame Rate), and conclude that VBR with SCD is one of the most suitable ATM service categories for accommodating best effort traffic.

ABR service is currently standardized to handle applications of data traffic in ATM network. As a flow control method, the rate-based flow control has been adopted and applied to manage the ABR service. Several control methods have been proposed, and the EPRCA is selected as one of the control methods by the ATM Forum. EPRCA is an excellent algorithm, but when the EPRCA is applied to the ATM network, several problems occur. One of the problems is the beat-down problem, which gives unfair allocation of transmission rate to connections. We propose a new control method which solves the beat-down problem. We will show that, by our proposed method, (i) the ACR is given fairly to every connection compared to the conventional method, and also (ii) the throughput is fair for both long-hop and short-hop connections, (iii) the ACR is proportional to the throughput, and finally (iv) the total throughput is larger than that of the conventional method. The fairness of the throughput in (ii) is measured by the fairness index. In (iii), being proportional means that the allocated ACR is close to the throughput and it is measured by the proportion index. The performance is evaluated by computer simulation.

In Asynchronous Transfer Mode (ATM) networks, congestion can be caused by unpredictable statistical fluctuations of traffic flows and fault conditions within the network. If congestion happens, then the network performance for the already established connection will decrease. ATM networks use the preventive congestion control mechanisms such as Usage Parameter Control (UPC) and Connection Admission Control (CAC) to avoid congested conditions. Knowing that many sources in ATM networks have variable traffic stream with different QoS characteristics, traffic management functions become necessary to control the traffic flows within the network. By using the signaling procedures at the call setup phase, the network and source reach an agreement for some traffic characteristic parameters. If the source violates the traffic parameters, then the probability of congestion increases. So the network must control the source traffic streams and detect well the violating cells. Therefore, fast detection of any violating source is one of the most important characteristics of a good traffic policer. In this paper we propose a fuzzy traffic policer with high ability in detection of violating sources. Our proposed fuzzy controller has two inputs, estimated passed mean cell rate and the current state of the counter. If the output of fuzzy controller is 1, then the input cell is detected as violating cell, otherwise it is a non-violating cell. Simulation results obtained from two traffic sources, show that the proposed traffic policer has better selectivity than the conventional leaky bucket. It is observed that our proposed traffic policer has better ability for mean cell rate control, peak cell rate control and burst duration control. Furthermore, it is observed that the proposed traffic policer outperforms the conventional leaky bucket specially when the dynamic behavior is considered.

For the reduction of the jitter originated from the cell losses in ATM network when CBR traffic is transferred on AAL5, we propose that the receiver maintain a timer whose expiration time is proportional to the cell time of the source traffic plus the standard deviation of the 1-point CDV of the received ATM cells. Moreover, to enhance the granularity of the error or loss detection mechanism in the AAL5 PDUs, we also modified the AAL5 PDU trailer fields so that each cell comprising the AAL5 PDU has a sequence number field. The simulation results show that the peak-to-peak PDV of the AAL5 PDU by the proposed method is less than 69.4% to that by AAL5. Moreover, the AAL5 user receives the same or more error-free transport packets in the proposed algorithm than those in the ITU-T AAL5 for the same network simulation environment.