Abstract: A network device of a communication network is configured to implement coordinated scheduling and processor rate control. In one aspect, packets are received in the network device and scheduled for processing from one or more queues of that device. An operating rate of a processor of the network device is controlled based at least in part on at least one of an arrival rate of the packets and a number of the packets stored in the one or more queues. As one example of processor rate control based on packet arrival rate, the operating rate of the processor may be controlled by accumulating a designated number of the received packets, determining an average arrival rate of the accumulated packets, and setting the operating rate of the processor based on the average arrival rate.

Abstract: A network device of a communication network is configured to implement coordinated scheduling and processor rate control. In one aspect, packets are received in the network device and scheduled for processing from one or more queues of that device. An operating rate of a processor of the network device is controlled based at least in part on an optimal operating rate of the processor that is determined using a non-zero base power of the processor. For example, the operating rate of the processor may be controlled such that the processor either operates at or above the optimal operating rate, or is substantially turned off. The optimal operating rate of the processor may be selected so as to fall on a tangent line of a power-rate curve of the processor that also passes through an origin point of a coordinate system of the power-rate curve.

Abstract: A resource allocation algorithm identifies a resource hogger in a wireless communication system data sharing arrangement and control shared resource overuse by the resource hogger. In one embodiment, the base station for a given sector in the system tracks the time-slot usage of each active user in the sector. If the usage for any user reaches a predetermined hogger threshold, normal target QoS enforcement is suspended for that user to allow more time slots to be allocated to the other, non-hogger users. When the resource hogger user's usage falls below the threshold, target QoS enforcement is returned to that user. Temporarily suspending target QoS enforcement for resource hoggers and allocating the remaining resources to other users prevents resource hoggers from deteriorating performance of the entire system.

Abstract: A network comprising a plurality of network devices is configured to implement scheduling for energy efficiency. In one aspect, a set of network devices interconnected in a line within a network is identified, and a common frame size is established. For each of the network devices of the line, active and inactive periods for that network device are scheduled in a corresponding frame having the common frame size, with the frames in the respective network devices of the line being time shifted relative to one another by designated offsets. For each of one or more of the active periods of each of the network devices of the line, received packets are scheduled for processing in that network device.

Abstract: A network device of a communication network is configured to implement coordinated scheduling and processor rate control. In one aspect, packets are received in the network device and scheduled for processing from one or more queues of that device. An operating rate of a processor of the network device is controlled based at least in part on an optimal operating rate of the processor that is determined using a non-zero base power of the processor. For example, the operating rate of the processor may be controlled such that the processor either operates at or above the optimal operating rate, or is substantially turned off. The optimal operating rate of the processor may be selected so as to fall on a tangent line of a power-rate curve of the processor that also passes through an origin point of a coordinate system of the power-rate curve.

Abstract: A network device of a communication network is configured to implement coordinated scheduling and processor rate control. In one aspect, packets are received in the network device and scheduled for processing from one or more queues of that device. An operating rate of a processor of the network device is controlled based at least in part on at least one of an arrival rate of the packets and a number of the packets stored in the one or more queues. As one example of processor rate control based on packet arrival rate, the operating rate of the processor may be controlled by accumulating a designated number of the received packets, determining an average arrival rate of the accumulated packets, and setting the operating rate of the processor based on the average arrival rate.

Abstract: A network comprising a plurality of network devices is configured to implement scheduling for energy efficiency. In one aspect, a set of network devices interconnected in a line within a network is identified, and a common frame size is established. For each of the network devices of the line, active and inactive periods for that network device are scheduled in a corresponding frame having the common frame size, with the frames in the respective network devices of the line being time shifted relative to one another by designated offsets. For each of one or more of the active periods of each of the network devices of the line, received packets are scheduled for processing in that network device.

Abstract: A technique for controlling a packet data network to maintain network stability and efficiently utilize network resources through mechanisms involving per-destination queues and urgency weights for medium access control. The technique jointly controls congestion, scheduling, and contention resolution on hop-by-hop basis, such that the length of queues of packets at a node does not become arbitrarily large. In one embodiment, queue lengths and urgency weights may be transmitted and received via medium access control messages.

Abstract: Disclosed is a method and apparatus for scheduling multiple carriers to service multiple users in a multi-carrier wireless data network. A data transmission in a multi-carrier wireless data system can be scheduled in frames comprising one or more time slots. For each frame, each of multiple carriers in each time slot of the frame are assigned to one of multiple users. Various objective functions can be used to assign the carriers to the users based on a weight for each user and a channel rate of each carrier for each user while preventing excessive carriers from being assigned to a user.

Abstract: A technique for controlling a packet data network to maintain network stability and efficiently utilize network resources through mechanisms involving per-destination queues and urgency weights for medium access control. The technique jointly controls congestion, scheduling, and contention resolution on hop-by-hop basis, such that the length of queues of packets at a node does not become arbitrarily large. In one embodiment, queue lengths and urgency weights may be transmitted and received via medium access control messages.

Abstract: A new approach is described for scheduling uplink or downlink transmissions in a network having remote terminals communicating with a central hub. The scheduler keeps track of a token count. The token count for a given remote terminal is incremented by a target amount in each pertinent timeslot, but is also decremented each time that the remote terminal is served. The amount of the decrement for one timeslot is the amount of data served, i.e., transmitted to or from the remote terminal, in that timeslot. In exemplary embodiments of the invention, the target amount by which T is incremented depends on the current value of T. Whenever the token count is non-negative (i.e., whenever it has a positive or zero value), the target amount is a desired floor, or lower limit, on an average amount of data delivered to or from the given remote terminal in one timeslot. Whenever the token count is negative, the target amount is a desired ceiling, or upper limit, on the same average amount of data delivered.

Abstract: Systems and techniques for scheduling of data transmission to remote mobile units so as to provide at least an acceptably low level of delay. A scheduler computes an urgency value for each data stream serving a mobile unit and sets the urgency value equal to the highest urgency value of a data stream serving the mobile unit. The scheduler computes a scheduling priority for each mobile unit based on a computation that takes into account the urgency value of the mobile unit and schedules the highest priority mobile unit for service, selecting the highest priority data stream serving the mobile unit scheduled for transmission. The urgency value for a data stream depends on the sensitivity of the data stream to delay and the delay experienced by the data stream. Computation of the urgency value may take into account a delay limit associated with the data stream.

Abstract: A resource allocation algorithm identifies a resource hogger in a wireless communication system data sharing arrangement and control shared resource overuse by the resource hogger. In one embodiment, the base station for a given sector in the system tracks the time-slot usage of each active user in the sector. If the usage for any user reaches a predetermined hogger threshold, normal target QoS enforcement is suspended for that user to allow more time slots to be allocated to the other, non-hogger users. When the resource hogger user's usage falls below the threshold, target QoS enforcement is returned to that user. Temporarily suspending target QoS enforcement for resource hoggers and allocating the remaining resources to other users prevents resource hoggers from deteriorating performance of the entire system.

Abstract: A method is disclosed for determining the admissibility of an offered session of traffic of a specified class to a server in a packetized communication network. Each class c has a peak traffic rate r(c). The server has a total processing rate C. Admitted packets are scheduled according to an EDF scheduling discipline. The method for determining admissibility comprises defining an operating point for the server. The operating point represents the number of sessions Nc of each respective class currently offered or currently being served. The method further comprises determining whether the defined operating point falls within a set of operating points that together define an admissible region. The admissible region consists of operating points for which the probability of violating a delay bound for any packet is below a threshold. The determination of the admissible region involves principles of statistical multiplexing.

Abstract: A new approach is described for scheduling uplink or downlink transmissions in a network having remote terminals communicating with a central hub. The scheduler keeps track of a token count. The token count for a given remote terminal is incremented by a target amount in each pertinent timeslot, but is also decremented each time that the remote terminal is served. The amount of the decrement for one timeslot is the amount of data served, i.e., transmitted to or from the remote terminal, in that timeslot. In exemplary embodiments of the invention, the target amount by which T is incremented depends on the current value of T. Whenever the token count is non-negative (i.e., whenever it has a positive or zero value), the target amount is a desired floor, or lower limit, on an average amount of data delivered to or from the given remote terminal in one timeslot. Whenever the token count is negative, the target amount is a desired ceiling, or upper limit, on the same average amount of data delivered.

Abstract: We disclose a method of dynamic channel assignment for wireless transmission systems that employ time or frequency multiplexing, or both time and frequency multiplexing. The invention is specifically addressed to the problem of avoiding interference in the channels of such systems. In a broad aspect, the invention involves partitioning base stations of a network into non-interfering sets. Channels are allocated to the non-interfering sets according to need. Stages of channel reallocation take place periodically. The reallocation takes place through coordinated activity by the base stations. That is, the channel reallocation is carried out in response to information that is exchanged between base stations, or it is centrally directed by the network in response to information passed to the network by the base stations.

Abstract: A method is disclosed, for designing an access network that is to carry communication traffic between end nodes and a core network. Information is provided that describes end node locations, the level of demand associated with each end node, available trunk types and their related capacities, and a cost structure. The cost structure includes a fixed overhead cost for each trunk type, and a service charge per unit distance for each trunk type. The provided information is incorporated in a linear program to find an optimal-cost access network. The linear program is solved to obtain a provisional solution that defines the composition and usage of each link of the optimal-cost access network. For each such link, the composition is defined by a fractional level of investment (incurring a like fraction of the corresponding overhead charge) in each pertinent trunk type.

Abstract: A packet routing technique which is stable for all networks in the presence of input blocking and output blocking. The packets injected within a network are examined and based on a historical perspective of those packets a determination is made on how to route individual packets throughout the network in a stable manner. In particular, in order to achieve complete network stability, individual switches within the network need to choose matchings, i.e., input to output port connections, that reflect the demand on each port-pair within the switches. Thus, if all packets are guaranteed to be in the network for at most a maximum number of time blocks, then a particular switch will have seen all the packets injected in the network at least that maximum number of blocks ago.