Abstract: Application service requests received by an application hosting framework are automatically differentiated and categorized, and resource usage patterns associated with the requests are predicted. Resource usage data points are successively extracted from the hosting framework. Elements of an initial resource usage pattern matrix are computed from the data points. An estimate for the number of categories of requests is computed from the initial resource usage pattern matrix, where the requests in each category have similar resource usage patterns. Elements of a resource usage signature matrix and request categorization matrix are computed from the estimate for the number of categories of requests and the initial resource usage pattern matrix.

Abstract: A traffic sensing system for collecting information on traffic conditions is provided. A traffic sensing system includes a traffic sensing server and a mobile traffic sensing device that sends traffic reports to the traffic sensing server. An MTS device may use an accelerometer integrated into a smart phone to detect potholes, to detect when the vehicle is braking, to detect whether the MTS device is being transported via a vehicle or a pedestrian, to detect horns sounding, and so on. The MTS device reports the various conditions to the traffic sensing server for accurate assessment of traffic conditions at stretches of road through which vehicles transporting MTS devices travel.

Abstract: Described is transparently compressing content for network transmission, including end-to-end compression. An end host or middlebox device sender sends compressed packets to an end host or middlebox device receiver, which decompresses the packets to recover the original packet. The sender constructs compressed packets including references to information maintained at the receiver, which the receiver uses to access the information to recreate actual original packet content. The receiver may include a dictionary corresponding to the sender, e.g., synchronized with the sender's dictionary. Alternatively, in speculative compression, the sender does not maintain a dictionary, and instead sends a fingerprint (hash value) by which the receiver looks up corresponding content in its dictionary; if not found, the receiver requests actual content.

Abstract: A client-based collaborative approach called WebProfiler is used for diagnosing Web transaction failures. The WebProfiler leverages end-host cooperation to pool together observations on the success or failure of Web transactions from multiple vantage points. These observations are utilized by a collaborative blame attribution algorithm to identify a suspect network entity that caused the Web transaction failure.

Abstract: Disclosed is a general model and method for computing performance bounds in multi-hop wireless networks. Rather than focusing on computing asymptotic performance bounds under assumptions of homogeneity or randomness in the network topology and/or workload, the present invention accommodates any given network, technology, interference model, routing paradigm, and workload. Using a conflict graph to formally characterize the impact of wireless interference on the performance of multi-hop wireless networks, methods for computing upper and lower bounds on the capacity of a given wireless network are detailed. Besides computing network capacity, the model and method disclosed can also enable or benefit other applications including maximizing fairness and minimizing maximum link utilization.

Abstract: An intelligent lookup service for a network is provided for clients of a network requesting services of the network that intelligently determines, based on a service requirement of the requested service, optimal service endpoint(s) for providing the requested service. The intelligent lookup service can incorporate predetermined mapping policy and traffic measurements into the determination. In addition, a feedback loop is provided from clients and/or service endpoints to the lookup service concerning measurements about prior connections in the network. The lookup service can include a set of beacons distributed in the network and against which measurements about the network are recorded. A client receives, from the lookup service in response to a request for a network address, a set of candidate service endpoints that pertain to the requested network address and the client connects to one of the candidate service endpoints based on policy or context.

Abstract: A electronic communication system that can detect and adapt to delays in delivery of e-mail messages. The system may adapt to delays by using other mechanisms to convey the information intended for delivery by e-mail. Though, other reactions to delays are possible, including rescheduling events premised on delivery of information by e-mail. The system may use a low-latency notification channel in parallel with a channel used for e-mail delivery to detect actual delays for a specific e-mail message. Additionally, the system may detect potential delays based on historical delay information or other information indicating that a path over which an e-mail is to be sent may be experiencing delivery delays and may adapt to a potential delay before a message likely to experience the delay is sent.

Abstract: A electronic communication system that can detect and adapt to delays in delivery of e-mail messages. The system may adapt to delays by using other mechanisms to convey the information intended for delivery by e-mail. The mechanism may convey the information to the recipient once the delayed electronic mail message is received by the recipient's e-mail system. In this respect, the recipient may make arrangements to receive information in the e-mail message when the recipient expects to be away from his or her e-mail system. Additionally or alternatively, the recipient may choose to initiate out-of-band communication to the sender when the recipient receives an indication of a delayed electronic mail message.

Abstract: A electronic communication system that can detect and adapt to delays in delivery of e-mail messages. The system may adapt to delays by using mechanisms other than the initially intended path to convey the information intended for delivery by e-mail. A possible adaptation is reprioritization of an e-mail message that is found to be experiencing a delay.

Abstract: A electronic communication system that can detect and adapt to delays in delivery of e-mail messages. The system may adapt to delays by using other mechanisms to convey the information intended for delivery by e-mail. Delays may be detected using a low-latency channel to send notifications of e-mails to recipients. The notifications are likely to be received in advance of a delayed e-mail, allowing an intended e-mail recipient to detect that delivery of an e-mail has been delayed. The recipient may adapt to the delay in delivery, when a notification is received without a corresponding electronic mail message. The notification may be small relative to an e-mail message but may include enough information to allow the recipient to identify the subject matter of the corresponding e-mail message, an importance level of the e-mail message, a preferred mechanism of the sender for out-of-band communications, and/or the location from which the e-mail was sent.

Abstract: A computer in a network runs a verification procedure in which it sends data packets to another computer in the network. Some or all of the data packets contain, either individually or collectively, a secret piece of information, such as a secret code. The computer then makes a determination regarding the network links between it and the other computer. If, for example, the other computer is able to respond by providing the secret piece of information back, then the computer sending the data packets concludes that the devices along the network links en route to the other computer are properly forwarding data packets.

Abstract: Disclosed is a general model and method for computing performance bounds in multi-hop wireless networks. Rather than focusing on computing asymptotic performance bounds under assumptions of homogeneity or randomness in the network topology and/or workload, the present invention accommodates any given network, technology, interference model, routing paradigm, and workload. Using a conflict graph to formally characterize the impact of wireless interference on the performance of multi-hop wireless networks, methods for computing upper and lower bounds on the capacity of a given wireless network are detailed. Besides computing network capacity, the model and method disclosed can also enable or benefit other applications including maximizing fairness and minimizing maximum link utilization.

Abstract: A new system and method of available bandwidth estimation applies even where the narrow link and tight link in a network path are in different locations. In embodiments of the invention, a unique packet probe series structure and processing is employed to estimate available bandwidth. In an embodiment of the invention, the spacing between probe packets is adjusted at the source to account for dilation caused by links leading to the tight link, so that the spacing is appropriate when the probes arrive at the tight link. Moreover, the multi-packet probe comprises a large packet followed by two much smaller packets. The large packet is then dropped once it has traversed the tight link. The two small packets, which are impacted little by subsequent narrow links, preserve the spacing set by the tight link, encoding the delay induced by the tight link, all the way to the destination.

Abstract: A data sequence may be encoded in a plurality of layers of multiple description coding. The layers of multiple description coding may include a first and a second layer of multiple description coding. The first layer of multiple description coding may include an initial part of a data sequence as well as forward error correction code for the initial part. The second layer of multiple description coding may include a next part of the data sequence as well as forward error correction code for the next part. A first set of data sequence breakpoints may be determined for the first layer of multiple description coding. A second set of data sequence breakpoints may be determined for the second layer. The data sequence may be encoded in the plurality of layers of multiple description coding as a function of the first and second sets of data sequence breakpoints.

Abstract: A computer network has links for carrying data among computers, including one or more client computers. Packet loss rates are determined for the client computers and, a system of equations is set up expressing the relationship between the loss rates at the client computers and the loss rates at the links. The system of equations is then solved using one or more linear programming techniques, and optimized by making an effort to find the most parsimonious solution.

Abstract: Disclosed is a general model and method for computing performance bounds in multi-hop wireless networks. Rather than focusing on computing asymptotic performance bounds under assumptions of homogeneity or randomness in the network topology and/or workload, the present invention accommodates any given network, technology, interference model, routing paradigm, and workload. Using a conflict graph to formally characterize the impact of wireless interference on the performance of multi-hop wireless networks, methods for computing upper and lower bounds on the capacity of a given wireless network are detailed. Besides computing network capacity, the model and method disclosed can also enable or benefit other applications including maximizing fairness and minimizing maximum link utilization.

Abstract: A technique is disclosed that can efficiently control congestion, while supporting heterogeneity for streaming data among multiple computers in a network. A plurality of nodes is divided into a plurality of distribution trees within a computer network, wherein the data is divided into a plurality of prioritized layers. When a node experiences packet loss, the location of the congestion is inferred. If the congestion is at or near the outgoing link, outgoing traffic is shed to alleviate the congestion by shedding child node(s) receiving descriptions in the least important layer of data that the child node(s) are receiving. Similarly, if the congestion is at or near the incoming link, incoming traffic is shed by shedding parent nodes that are sending descriptions in the least important layer of data that the node is receiving. Nodes with available bandwidth are further instructed to subscribe to additional descriptions.

Abstract: A system is disclosed for collaborative downloading that uses both the WLAN and the WWAN in combination, in an attempt to bridge the range-speed dichotomy. Devices in close vicinity band together their WWAN links, with the high-speed WLAN serving as the glue, to boost the effective wide-area bandwidth available to the active nodes.

Abstract: A computer network has links for carrying data among computers, including one or more client computers. Packet loss rates are determined for the client computers and, based on the loss rates, a number of possible sets of solutions for the loss rates at each of the links are generated. The sets of possible solutions are subjected to a statistical analysis. Based on the results of the analysis, a determination is made regarding which of the links are excessively lossy.

Abstract: A local network coding framework and method including techniques to improve efficiency in a wireless network by reducing overhead. The local network coding method includes exchanging data availability between nodes on the wireless network by sending Bloom filters of lists of packets to neighboring nodes. Based on data availability, optimized mixing of pure packets is performed to form mixture packets for output. A separate acknowledgement buffer keeps track of the pure packets transmitted but not acknowledged. If an acknowledgement does not arrive after a certain time period, the packet is assumed to be lost and is retransmitted. An optimized packet mixing process generates mixture packets and decides which nodes to send the mixture packets. The local network coding framework and method also includes methods for representing the composition of a mixture packet and using mixing at a wireless access point to improve the performance of the wireless local area network.