Abstract: A best-effort bandwidth allocating method, includes the steps of: measuring sending amounts of packet data that are input from each of ports providing minimum bandwidth guarantee type and best-effort type communication service; calculating statistical information corresponding to an accounting subject time period of the sending amounts of the packet data of the best-effort bandwidth of each of the ports, based on the result of the measurement; changing a value of a peak information rate of a port sending out more of the packet data at a contracted communication rate to be low based on the statistical information; and impartially allocating the best-effort bandwidth to each of the ports based on the value of the peak information rate and a minimum bandwidth guarantee rate.

Abstract: A method for time-based synchronization of multiple media streams transmitted over a communications network, such as the Internet, by multiple, independent streaming media sources. First and second media streams of data packets are received from first and second media sources. Timing data is parsed from the two media streams, and first and second transmission delay values are determined by comparing the timing data with a reference time. A synchronized media stream is created by combining the first and second media streams into a time-synchronized media stream with adjustments to correct for calculated transmission delay values. Feedback signals are sent to the media sources to control transmission variables such as stream length, transmission rate, and transmittal time to manage the variable delay at the media source. The first and second media streams are decoded into intermediate media streams compatibly formatted to allow mixing of the streams and data packets.

Abstract: Numerous embodiments of a method and apparatus for managing network traffic are disclosed.

Abstract: A system for the assessment of network performance criteria, and applying this criteria to the classification of network addresses into appropriate ranges, using these ranges to consolidate performance measurements for the associated addresses, and applying these metrics toward the optimization of the network towards performance or policy objectives.

Abstract: A method is disclosed for call and/or connection acceptance control and the optimal delivery of multimedia (audio/video) data over networks. This method involves the establishment and monitoring of certain criteria which may be used to maximize the number of simultaneous clients without sacrificing quality-of-service for already-connected clients. Methods are disclosed for maximizing total throughput as well as maximum charge models for different levels of service. The disclosed methods solve these optimization problems by expanding on linear-program techniques in manners geared towards multimedia content delivery over networks and many variations suitable for varying business models are disclosed.

Abstract: Digital circuits and methods for designing digital circuits are presented. In an embodiment, a number of bits (B) of a bit-stream to be processed in parallel by a digital circuit is selected. A clocking rate (C) is selected for the digital circuit such that a product (P), P being equal to B times C, is equal to at least 1 gigabit per second. An initial circuit capable of serially processing the bits of the bit-stream at a data processing rate less than P is formed. This initial circuit includes a feedback loop having N+1 delays. N is a whole number greater than zero. The initial circuit is unfolded by a factor of B to form B parallel processing pipelines for the bits of the bit-stream. An N-step look-ahead network is formed to provide inputs to the B parallel processing pipelines. The unfolded circuit is retimed to achieve the selected clocking rate (C).

Abstract: Method and devices are provided for allocating network resources in a flexible manner. In some implementations, a customer's unused resources for a particular type of service are assigned to another type of service. In other implementations, a first customer's unused resources are assigned to a second customer, e.g., in exchange for a relatively lower service charge to the first customer. The unused bandwidth may be assigned on a hierarchical or a non-hierarchical basis. In preferred embodiments, resources are allocated using a token bucket methodology. Preferably, high-priority resources are not compromised by the allocation scheme. The discipline or manner in which resources or bandwidth are shared may be specified in a static fashion or information regarding the state of congestion in the network maybe used to generate a dynamic (time varying) specification.

Abstract: A multimedia packet re-multiplexer system having a plurality of multimedia sources, each multimedia source sending incoming multimedia packets, each packet having a header which includes a packet identifier (PID) to determine the packet type. The system includes an interface multiplexer (mux) for periodically scanning the multimedia sources for the incoming packets. The system also includes a main storage device for storing each incoming packet, a secondary storage device having a cut-through mechanism for storing the header of each incoming packet, an input classifier for selecting a process for each packet stored in the main storage device, in accordance with the corresponding header from the secondary storage device.

Abstract: A method and mechanism for determining when to transmit a probe packet to detect increases in path maximum transmission unit (PMTU) in a network having a host and a target interconnected by the network. Calculate a utility variable corresponding to a number of packets to be transmitted from the host to the target which are greater than a predetermined amount of a known PMTU for the target. When the utility variable is greater than a predetermined utility threshold, sending instructions to the host to send a probe packet to detect increases in PMTU for the target. Storing the previous state of the internet path with respect to PMTU in a variable PPMTU and tracking it during decreases so that a restoration of the PMTU can be verified by sending probes. PMTU is treated as a resource which is either fully or partially used by an application.

Abstract: A system and method for controlling call admission control in a mobile communication system enables call admission control function to be conducted in a forward link of the mobile communication system. The call admission control method includes a call admission control process, in which voice calls and data calls are distinguished from each other, minimum resource availability is checked, a voice call priority function is conducted, and a maximum supplemental channel (SCH) for the data call is established. According to this process QoS (Quality of Service) for all users is satisfied to the greatest extent and the occurrence of call reject and call drop of voice calls and data calls are reduced. Further, the voice call priority may be guaranteed and the database related to the call admission control may be adjusted easily by the system operator according to the relevant cell environment.

Abstract: Improved algorithms are provided for performing path management for a plurality of select data transmission sessions in a multicast network. The algorithms include: constructing a weighted graph which represents topology of the network; assigning load correlated costs to network links; and computing least cost paths for each of the data transmission sessions which accounts for global bandwidth utilization.

Abstract: A flexible scheduling method with tunable throughput maximization and fairness guarantees in resource allocation is required and suitable for high-rate packet data and other services. Our inventive method, named Alpha-Rule, employs a control variable ?, that permits dynamic and/or real-time adjustment/tradeoff between aggregate throughput, per-user throughput, and per-user resource allocation. Our method advantageously operates in conjunction with Multiple-Input Multiple-Output techniques such as Space-Time Block Coding (STBC), Bell Labs Layered Space-Time (BLAST) and others, while offering greater flexibility than existing scheduling techniques, e.g., max-C/I or Proportionally Fair (PF).

Abstract: The invention provides an ATM switch which realizes hierarchical shaping for each virtual channel and each virtual path with a simple configuration. Cells are sent from cell buffers of an ATM core switch by FIFO operation to output side connection information application sections of output side circuit interfaces. In each of the output side circuit interfaces, the output side connection information application section acquires connection information such as a service class based on an intra-switch connection identification number applied to each cell and applies the connection information to the cell. An output cell buffer queues cells for each virtual channel. A VC cell rate control section reads out cells from the output cell buffer in accordance with the connection information and performs traffic priority control and rate control of the cells to be outputted.

Abstract: A send client can send a message comprising multiple message segments to a receive client via a computer network. A data exchange server can receive the message segments sent by the send client and store these message segments in a storage device. The data exchange server can also send the message (once all the message segments are received) to a receive client. For each message segment to be sent to the receive client, the data exchange server can calculate a transmission rate for the message segment based upon current network throughput and send the message segment to the receive client at the calculated transmission rate.

Abstract: A flow control system include a congestion detecting section and control section. The congestion detecting section detects congestion in a packet switching network. The control section is arranged in a transmitting node. When the congestion detecting section detects congestion, the control section calculates a new transmission packet rate. When the new transmission packet rate is smaller than a current transmission packet rate, the control section changes the current transmission packet rate to the new transmission packet rate after transmission of data to be transmitted to a receiving node. A flow control method is also disclosed.

Abstract: In summary, a method and apparatus for performing a connection admission control in an asynchronous network node is disclosed, wherein approximation parameters obtained by approximating a traffic parameter function defining an effective bandwidth of a connection are stored and used to determine a value representing an effective bandwidth of a requested new connection. Since the approximation parameters are calculated in advance and stored, the determination of the effective bandwidth of a requested connection can be performed by simple calculations based on the stored approximation parameters. Thus, the invention presents an extremely simple CAC procedure which is accurate enough to take full advantage of statistical multiplexing. Due to the fast calculations, the connection admission control method and apparatus are suitable for real-time connection admission control decisions.

Abstract: The invention relates to a procedure for the transmission of data in variable time slots between a controller of a packet-oriented data network on the one hand and a terminal of a user of the data network on the other hand, time slots for the data transmission being assigned to a terminal following request made by the terminal and in dependence on the transmission capacity available in the data network. In order to create the possibility of enabling known data networks for the transmission of data in variable time slots to be used also for QoS applications without restriction of the functionality, it is proposed that the data transmission rate be monitored separately for each data flow of a terminal of the data network.

Abstract: The invention herein described consists of an algorithm, which performs an end-to-end estimation of the bandwidth available in an end-to-end connection established between a server and a client via a packet switching network such as the Internet Protocol Network (IP). This algorithm is used to properly regulate the input rate at the send side. Typical applications are delivering best effort traffic over TCP, or audio and video traffic over RTP/UDP. The invention is particularly effective over wireless Internet and can be used in a content delivery system to dynamically choose the best server between a set of servers to satisfy the request of a client, or to select the best route in a content deliver or global hosting system.

Abstract: In a particular embodiment, the present disclosure is directed to a data communications system. The data communication system includes a plurality of digital subscriber lines, a digital subscriber line multiplexer coupled to each of the plurality of digital subscriber lines; and a data switch coupled to the digital subscriber line multiplexer via a communication link. The data communications system is configured such that the number of digital subscriber line users supported by the digital subscriber line multiplexer is determined based on an estimated maximum number of users, the estimated maximum number of users determined based on an average peak bandwidth per user value, a data communication capacity of the communication link, and a data transmission slowdown indicator.

Abstract: In a particular embodiment, the present disclosure is directed to a data communications system. The data communication system includes a plurality of digital subscriber lines, a digital subscriber line multiplexer coupled to each of the plurality of digital subscriber lines, and a data switch coupled to the digital subscriber line multiplexer via a communication link. The data communications system is configured such that the number of digital subscriber line users supported by the digital subscriber line multiplexer is determined based on an estimated maximum number of users, the estimated maximum number of users determined based on an average peak bandwidth per user value, a data communication capacity of the communication link, and a data transmission slowdown indicator. The communication capacity is based on a user type selected from a set of available user types.

Abstract: An apparatus and process for relabelling and redirecting at least some of the read transaction data frames and the write transaction write data and transfer ready frames in a network so as to bypass a storage manager and pass directly between the client and a storage device via a switch. This eliminates the storage manager as a bottleneck. Some embodiments redirect every read and write transaction, and others redirect only large transactions, or only ones not stored in cache or when latency gets too high. Redirection is accomplished by transmission from the storage manager to a switch redirection commands that contain old and new address data. When a frame to be redirected comes in, its address is compared to the old address data. If there is a match, the new address data is substituted and the frame is passed to a conventional routing process to be routed so as to bypass the storage manager.

Abstract: A ring network provides transparent local area network (LAN) service by allocating respective proportions of data transmission capacity of the ring to different closed user groups (CUGs), each including a plurality of LAN clients. At each node of the ring, the use of a connected segment of the ring is monitored for both pass-through and locally-generated traffic by the LAN clients on a per-CUG basis. When it is detected that use of the connected segment for a CUG is approaching the allocated proportion, an active LAN client of the CUG is selected and sent a throttle message indicating that the LAN client is to reduce its data transmission rate. Rate monitoring for is accomplished using a “leaky bucket” mechanism. A “rate cache” identifying the active senders and their transmission rates can also be used in selecting a LAN client for receiving the throttle message.

Abstract: An improvement for a phasor fragmentation engine and method, whereby a phasor flipping algorithm is applied when determining fragment phasors for a non-constant envelope modulation signal (e.g. OFDM). The phasor flipping algorithm avoids sharp phase transitions for the fragment phasors, which cause an increase in bandwidth, by performing a comparison of the phasor angle separation between the prior and current time samples. This comparison corresponds to a determination of whether the modulation signal V has passed near or through zero.

Abstract: A modular switch, comprising a plurality of backplane sub-buses; a plurality of cards which are each allocated one or more of the backplane sub-buses; and a controller which dynamically allocates the backplane sub-buses to the plurality of cards, based on the bandwidth needs of the cards. Preferably, the bandwidth capacity of substantially all the backplane sub-buses is less than the sum of the maximal transmission bandwidth capacities of the cards.

Abstract: A virtual path feature in which several virtual channels share an assigned amount of bandwidth is implemented in a network processor. The network processor maintains a schedule indicative of respective times at which a plurality of virtual channels are to be serviced. An entry is read from the schedule. The entry corresponds to a current transmit cycle and includes a pointer to a channel descriptor for a virtual channel to be serviced in the current transmit cycle. A data cell for the virtual channel to be serviced in the current cycle is transmitted. An entry is added to the schedule to point to a channel descriptor that is pointed to by the channel descriptor for the virtual channel serviced in the current transmit cycle.

Abstract: A wireless network includes a plurality of proxy servers located at various locations to selectively transform data based upon network conditions, such as link congestion. A queueing model for the network can be used to determine optimal operating parameters for the network.

Abstract: A method for controlling data flow including: measuring an source specific incoming data rate of one source; comparing the source specific incoming data rate with a corresponding predetermined data rate; if the source specific incoming data rate exceeds the predetermined data rate, eliminating incoming data packets for reducing the source specific incoming data rate to be smaller than the predetermined data rate, if the source specific incoming data rate does not exceed the predetermined data rate, transmitting the incoming data packets to switching means, connected to said input port, characterised in that a backpressure warning signal (bpws) is generated if the source specific incoming data rate exceeds at least one of the at least one predetermined data rates and said generated backpressure warning signal is sent to a source of the incoming data packets. Hereby further transmission of data packets is prevented.

Abstract: The present invention provides methods and apparatus for transmitting multicast data over a wireless channel. At least one wireless terminal requests a multicast service corresponding to at least one requested layer. A wireless infrastructure comprising a base station and a node determines a data rate that the at least one wireless terminal can receive reliably and correspondingly configures a multicast session for at least one layer. The node utilizes measurements provided by the wireless terminal. The node through the base station signals the wireless terminal about a link-level multicast address corresponding to a time slot for which the wireless terminal shall process packets. An associated point of attachment with a core data network controls a data flow from a multicast content source through the core data network in order to match the data rate over the wireless channel.

Abstract: A wireless communication system is described for allocating limited network access according to priorities designated for requested transactions of wireless communications. The wireless network has a number of access links for transmitting transactions for wireless communications. A plurality of wireless communications devices request transmission of transactions on the wireless network. A designated priority level is associated with each transaction. In response to the transaction requests, an access control manager in the wireless network schedules transmission of transactions when all of the plurality of access links are occupied, by authorizing a transmission of a transaction of higher priority than another transaction that is being transmitted, and discontinuing the transmission of the transaction of lower priority.

Abstract: A method for managing an asynchronous transfer mode (ATM) cell includes transmitting an ATM cell from a server system to a broadband modem. The ATM cell is forwarded from the broadband modem to a client system.

Abstract: The present packet scheduling algorithm gives cellular network operators greater flexibility in adjusting the way resources are allocated among interactive best-effort data users. Best effort data users with different radio link qualities may have different amounts of data delivered to them using the same amount of radio resource. In the context of link adaptation, this characteristic complicates the fairness issue in cellular environments and has a profound impact on the overall system performance. As a result, the present packet scheduling algorithm is capable of allocating radio resource dynamically, not only based on channel conditions, but also to achieve different performance trade-offs among users with different link qualities. According to the algorithm, channel quality is determined for each user, channel efficiency is calculated and the channel efficiency value is used as the primary factor in weighting the delivery of packets to (or from) a given user.

Abstract: A system includes servers accessing storage through a storage area network. The storage has a plurality of ports which may differ in data transfer speed, and memory resources connected to these ports. Data transmission between a port and a server is monitored. If the amount of data transfer exceeds prescribed limits, then a different port is selected, and that port is used for further communications.

Abstract: A communication system that includes multiple nodes controls a flow of data from a first node of the multiple nodes to a second node of the multiple nodes without relying on an estimate of a rate at which data is drawn from a buffer of the second node and such that an overflow and an underflow of the buffer is avoided. The second node determines multiple flow control parameters, including a current occupancy (Q) of the buffer and an upper threshold (U) and a lower threshold (L) for an occupancy of the buffer and determines a desired data rate (r) based on the multiple flow control parameters. The desired data rate can be used to adjust a data rate for the flow of data. In another embodiment, the communication system further dynamically controls a rate at which flow control messages are conveyed by the second node to the first node.

Abstract: The invention is directed to a method for controlling delays in a cellular telecommunications network. The delay control method according to the invention is based on a hierarchical structure of delay controlling entities, which preferably communicate only with entities directly above or below them in the hierarchy. In the downlink direction, an entity receiving data, such as a base station or a splitting unit, sends a timing report to the entity sending the data if the data is received too early or too late, whereafter the sending entity may adjust the sending time of data. The same reporting and adjusting process may be repeated through all levels of the control hierarchy, resulting in a collective control of delays from the top of the hierarchy, for example from a RNC, to the bottom, for example to a base station.

Abstract: A method for adaptively partitioning a buffer in a shared buffer switch is provided. The buffer partitioning method for a shared buffer switch which has a plurality of input ports, a plurality of output ports, and a shared buffer, the method for determining whether or not to store a cell, which is newly received through one of the input ports, in the shared buffer comprises the steps of (a) determining a buffer area of the shared buffer in which the newly received cell is stored; (b) determining a cell discard threshold with respect to the total number of cells stored in the shared buffer and the changing rate, with respect to time, of the total number of the cells; and (c) determining whether or not to store the newly received cell in the shared buffer, by comparing the number of cells stored in the buffer area in which the newly received cell is to be stored, with the cell discard threshold.

Abstract: This patent concerns a system and method for detecting a mass calling event in a telephone system and to regulate telephone calls to a call destination for which a mass calling event has been detected where a packet transport network and Call Server is integrated into the Public Switched Telephone Network (PSTN). A packet transport network and a central Call Server implement switching functionality traditionally provided by numerous Time Division Multiplexing (TDM) switches within the PSTN. A credit bucket mechanism is used for call regulation in a mass calling event. The packet network may be based on (but is not limited to) ATM, Frame Relay, or IP packet protocols.

Abstract: A method for dynamic division of the radio capacity in a Time Division Multiple Access (TDMA) system between different packet radio services. Each packet radio service is composed of packets with the same or different priority. Several MSs can share a time slot. Information regarding to the interference for each MS is obtained by a request from a mobile station (MS) or through a traffic measurement at the base transceiver station. This information, along with the QoS contract, is used as criteria in allocating more time slots to packet radio service. A framework of dynamic scheduling for mobile communication (DSMC) comprising a Channel Codec Unit (CCU) and a Packet Control Unit (PCU) determines the service rate upon the required QoS of a user and the interference level.

Abstract: The present invention defines a method and apparatus to extend class-based queuing (CBQ) with multiple “behavioral” queues per class, to include a dynamic weighting mechanism between these queues. The packets are forwarded from the behavioral queues according to the weighting assigned to each queue. The weighting for packet scheduling of the queues is adjusted to account for additional flow going through the queues. The weight of a queue is controlled relative to the weight available to other queues. When a flow is reclassified, the queue weights is readjusted accordingly. Well behaved flows experience low delay and can thus achieve a fair bandwidth allocation without having to have multiple packets queued to compete with non-adaptive aggressive flows.

Abstract: A method and a system using the method enabling to decrease required resource for the bandwidth reservation in an inter-site connection network used for communication between communication sites. The aggregation of bandwidth is considered for allocating bandwidth in the inter-site connection network. The network consists of a plurality of nodes each having a packet switch, and a plurality of user sites each constituted by a host or an internal network respectively connected to the plurality of nodes via access lines. With respect to the plurality of user sites, when one user site is to be connected to the other site through the network, a necessary and sufficient bandwidth for interconnecting between the user site and the other is calculated according to the bandwidth of the access line connecting the user site to the network considered as a minimal bandwidth. Based on the calculated result, the bandwidth is allocated to the plurality of nodes.

Abstract: A method (20) and corresponding equipment for correcting misalignment of respective pointers in a UE device (11) and a Node B (10) for indicating a maximum allowed rate of uplink from the UE device (11) to the Node B (10).

Abstract: A metering device has a first token bucket with a profile, a rate, and a maximum number of tokens. The device has another token bucket with its own profile, two associated rates, and a maximum number of tokens. In operation, the device monotonically increments the number of tokens in the first token bucket at its rate if the bucket has less than the maximum number of tokens for that bucket, and monotonically increments the number of tokens in the other token bucket at the same rate if the first token bucket is full and the other token bucket is not. Additionally, the device monotonically increments the number of tokens in the second token bucket according to the second rate associated with the token bucket if it is not full.

Abstract: In a class of minimum cost flow control (MCFC) algorithms for adjusting session rates or window sizes congestion control is achieved through consideration of an incremental cost function that addresses link congestion, and an incremental cost function that addresses the cost of providing less than the desired transmission rate. A coarse version of the algorithm is geared towards implementation in the current Internet, relying on the end-to-end packet loss observations as indication of congestion. A more complete version anticipates an Internet where sessions can solicit explicit congestion information through a concise probing mechanism.

Abstract: An operating method of a storage area network system which conducts transmittance of data by a plurality of servers accessing a storage through a storage area network, the storage area network system operating: obtaining and monitoring a data transfer amount between the respective servers and the storage; comparing a prescribed data transfer amount prescribed by the server and the obtained actual data transfer amount; selecting one of a plurality of ports provided in the storage according to the comparison result; and providing the relevant server an instruction to connect to the selected port.

Abstract: A computer dispatcher connected to one or more respective network buffers has stored file lists that identify one or more of the files in the database that are to be transmitted over networks connected to the respective network buffer. A scheduler(s) schedule one or more portions of one or more of the files to be written to the respective network buffers by defining transmission criteria about each of the files in the file list. These transmission criteria include a quantity to transmit criteria, defining a quantity of one or more of the portions of the respective file to transmit, and one or more release times. The release times define the time at which the respective portion is to be written to the network buffer. The system includes a dispatching process that determines an available space on one or more of the network buffers and a current system time.

Abstract: A method is disclosed for efficiently determining exact loss rate, or a loss curve, for a traffic source transmitted at a specified rate. The loss curve of a traffic source characterizes the loss rate of the traffic stream as a function of the allocated buffer size for a given transmission rate. Utilization of loss curve characterization allows for optimal resource allocation for a given source within a packet network. The present invention provides a deterministic method for computing the loss curve of a traffic source, examples of which include multimedia streams, elementary video streams, and MPEG-2 transport streams. The present method exploits the piecewise linearity of the loss curve and computes only the points at which the slope of the loss curve changes. The method is memory efficient and executes rapidly, for instance, a loss curve for a two-hour elementary video stream was determined within eleven seconds on a conventional Sun Ultra-2™ workstation.

Abstract: An approach for allocating system capacity of a communication switching system for exchange of traffic is disclosed. The system includes multiple terminals that request allocations of system capacity. The capacity is partitioned into a provisioned portion and an unprovisioned portion, in which a portion of the terminals constitutes a pool having a plurality of sub-pools. According to one embodiment, a control computer communicates with the plurality of terminals and allocates the provisioned portion of the capacity to the plurality of sub-pools of the terminals. The provisioned portion of the capacity is arranged into sub-partitions, wherein one of the sub-partitions is not associated with the sub-pools of terminals. Remaining sub-partitions are associated with the sub-pools of terminals.

Abstract: A requesting terminal includes an interface that allows a user to select whether data downloaded from a network (such as the Internet) is transmitted to the requesting terminal via a high-speed link, such as a satellite link, or a lower speed link, such as a terrestrial link. Preferably, the terrestrial link (which may comprise a conventional dial-up Internet connection) is a two-way link, wherein the requesting terminal transmits data requests to the network via the terrestrial link. The data requests generated by the requesting terminal are modified to designate whether the requested data should be downloaded from the network via the terrestrial link or the satellite link. The terrestrial link may also be automatically selected for certain applications.

Abstract: A method and apparatus for controlling congestion at a node in a data network. The node includes an input for receiving traffic units from the network, an output for releasing traffic units to the network and a control unit. The control unit is responsible for estimating a level of data occupancy of at least a portion of the network by looking at the traffic units received at the input from a remote node in the network. When the data occupancy level reaches a certain threshold, the node issues a control signal to the remote node such that the remote node lowers its rate of traffic units input in the network. By estimating the network data occupancy level, congestion at the node can be effectively foreseen and controlled.

Abstract: In an ATM switch, a correspondence between shapers which compose a shaper section and an output circuit(s) is not set up in an initial condition. At the time of a connection set-up, a connection control section interrogates a shaper/circuit control section about a corresponding relationship between the shaper(s) and the output circuit(s). In the case where a shaper(s) corresponding to an assigned circuit number is registered in a shaper/circuit-related table in the shaper/circuit control section, the shaper(s) is chosen. On the other hand, in the case where a shaper(s) is not registered in the table, after a new shaper(s) is registered in the table, a correspondence between the assigned circuit number and the shaper(s) is set up to the shaper section and a circuit interface section, and the corresponding shaper(s) is chosen.

Abstract: A device for Connection Admission Control for an ATM switch, intended for admitting to the switch a requested ATM connection of the DBR type, such that the “Quality of Service” of all ATM connections of the DBR type in said switch continues to satisfy certain conditions. For the composite traffic stream of DBR connections at an output port with capacity C, a single buffer with capacity B is available, while as boundary condition it holds that the total average load of the output port does not amount to more than ?×C, where ? is a constant with a value between 0 and 1. The CAC device comprises two sub-devices, which each execute a—rather complex—partial calculation, resulting in a positive or negative admission signal. The new ATM connection is only granted admission to the switch if both sub-devices emit a positive admission signal.